business intelligence teams

Abstract: Natural-language query generation over large knowledge graphs embodies the classical vocabulary problem in human-systems communication. Questions express concepts through wording and compositions that can differ substantially from the target schema, while limited model context requires selective access to schema information. We present an NL2SPARQL framework that places conceptual compositionality at the center of query interpretation and connects it to the relational composition required for binding and query construction. A fixed concept encoder represents compound expressions jointly, and schema candidates are ranked using semantic similarity, type compatibility, and hierarchy proximity. Reflective refinement critically examines how the grounded meanings are realized through argument bindings, joins, and operator scope. Diagnosed semantic discrepancies guide revisions to the responsible stage. We formalise a monotone refinement discipline that accumulates scoped interpretation requirements and establish conditions under which changes to the composed process preserve previously validated interpretations. Across five benchmark/knowledge-graph targets, mean schema recall@10 increases from 0.712 to 0.837. With retrieval held fixed, reflective prompt rewriting adds 2.27-3.33 answer-F1 points. These experiments evaluate the grounding and refinement mechanisms, while the formal analysis specifies the stronger requirements for conservative adaptation across queries.

Abstract: Existing long-document QA benchmarks rarely combine large-scale human-authored questions with detailed visual evidence annotations, limiting diagnosis of evidence localization and interpretation failures. We present VELD-QA, a large-scale benchmark for Visual Evidence grounding and question answering in Long Documents. It contains 15,000 fully human-authored question-answer pairs across 5,859 real-world PDFs totaling 372,445 pages, balancing chart, table, and complex-layout tasks. Human annotations identify supporting pages and evidence elements and describe cited visual content, enabling separate retrieval and interpretation evaluation. We evaluate nine vision-language models under four evidence settings and seven retrieval-augmented and agentic systems. Our analysis identifies bottlenecks in evidence localization and interpretation. Retrieval-based methods substantially underperform the oracle setting with ground-truth supporting pages; full-document access does not close the gap. Localization alone is insufficient: oracle accuracy peaks at 81.7%, highlighting persistent visual interpretation and reasoning challenges. Enriching inputs with our visual-element annotations narrows the performance gap by 17-24%, demonstrating value beyond evaluation and motivating data enrichment for multimodal document QA. Our code is available at https://github.com/oracle-samples/veld-qa.

Abstract: Inside organizations, a question's data often sit with several owners, who query their own tables but never hand them over. An LLM coordinator can fan out, sending the question to every owner at once, or relay, querying owners in turn and reusing earlier rows. We show that neither is safe in advance, because data ownership decides which one is right. Across thirteen settings on PeopleJoin and BIRD with three model families, fan-out is more accurate in twelve on questions one owner can answer, yet answers at most 4.3% of those joining two owners' tables. The flip follows ownership, not query shape: on BIRD two-table joins, fan-out answers 32-44% when one owner holds both and 1-4% otherwise. Relay wins by conditioning on returned rows, and hiding them from an otherwise identical planner cuts two-owner accuracy from 23.2% to 5.1%. Since ownership is public, we propose Ownership-Aware Routing (OAR), which drafts a schema-only SQL query, counts the owners whose tables it joins, and routes the question before any private row is read. In ten settings OAR is never significantly less accurate than the best fixed protocol, and beats every fixed protocol on PeopleJoin, by up to 9.3 points on held-out organizations.

Abstract: Table reasoning with language models typically assumes access to clean textual tables. In practice, tables are often serialized into text, which can corrupt cell contents, distort structural relationships, and discard visual cues, leaving the model to reason over incomplete evidence. In contrast, table images retain this information, but using it requires both accurate perception and reasoning grounded in the relevant cells. To address this, we propose MERIT (Multimodal Evidence Reasoning over Image Tables), a three-stage framework for learning to reason over table images, with serialized tables serving as optional auxiliary inputs (if provided). Our analysis identifies visual evidence acquisition as a bottleneck, motivating table-specific encoder adaptation through reconstruction, localization, and color-conditioned supervision. Building on the adapted representations, supervised fine-tuning teaches explicit evidence selection and reasoning using verified trajectories. Finally, reinforcement learning refines the policy with separate rewards for evidence correctness, calculation, final answers, and output format. By providing feedback on intermediate steps, the framework targets retrieval and computational errors that final-answer supervision alone does not distinguish. We evaluate the approach on table question answering and fact verification, analyze the contributions of visual inputs and training components, and assess generalization to additional datasets with different table structures and visual presentations.

Abstract: Financial Artificial Intelligence (AI) governance and model risk management (MRM) emphasize independent validation, transparency, and effective challenge of AI-generated computations. Text-to-SQL translates natural-language questions into Structured Query Language (SQL), but queries that agree on one database can still express different computations. We present VeriPIE, a neurosymbolic framework combining language-model generation with symbolic checks. It ensembles direct SQL generation with QuerySketch, a structured plan language checked by a backend implemented in Lean, a theorem prover and programming language. Plan diagnostics guide repair before SQL generation, while execution agreement and bounded searches for distinguishing databases inform candidate selection. These checks expose malformed plans and hidden disagreement without proving agreement with the user's intent. In single-run experiments on the complete Spider development set, VeriPIE achieves 72.05% test-suite accuracy (745/1,034), compared with DeepEye's 65.67% (679/1,034). Its two-query shortlist covers 78.43% (811 questions), compared with 74.66% for DIN-SQL (772) and 69.05% for DeepEye (714). On BIRD, VeriPIE reaches 68.90% execution accuracy and 73.73% two-query coverage. The central benefit is reviewable evidence about the generated computation: explicit plan checks, repair diagnostics, and concrete disagreements that support safer financial analysis.

Abstract: Conversational analytics lets people ask questions of records spread across many systems and get answers in plain language; it is useful only if each answer can be trusted and explained. A production system of this kind attaches a confidence score to every answer it writes over a database and uses it to show the answer, show it with a warning, or withhold it. The score's weights, caps and thresholds were set by design. This paper audits that design. On the 1,534 questions of BIRD dev, answered by GPT-5.1 with a benchmark-adapted production prompt and five samples per question, the designed score separates right from wrong answers weakly (AUROC 0.624, 95% CI 0.595-0.652) and withholds 35.7% of correct answers. Nearly all of its ranking signal comes from agreement among the samples, and most of it is lost where agreement is combined by a minimum with a checklist that drops to zero on any unsupported claim, including claims in commentary. We froze a rule in which agreement with the shown answer is the score and deterministic checks act as vetoes and caps, and pre-registered a test on Spider dev before any Spider answer existed. The primary hypothesis held: AUROC rose from 0.566 to 0.725 (paired difference +0.159, 95% CI +0.097 to +0.221), and correct answers withheld fell from 49.0% to 8.8% with PASS accuracy 95.7%. Under one matching policy the choice of agreement statistic matters little; the gain comes from how agreement enters the score. Whether added checks help depends on how correctness is defined, while they always cost unqualified coverage. A pre-registered empty-result check did not meet its effect-size criterion on Spider. Correctness here means the core answer; labels are model-judged, and a blinded two-person audit, not yet complete, will be reported in a revised version.

Abstract: Real-world tables are often heterogeneous, combining numerical features with free-form string columns. Table foundation models (TFMs) excel on numerical tables but require strings to be encoded numerically, while large language models (LLMs) hold semantic knowledge but are not designed for tabular predictions. Most existing bridges use LLMs as plug-in encoders for cell strings, yet how to extract representations effectively for tabular learning remains underexplored. We show that the interface between LLMs and tables matter as much as the LLM itself. Applied cell-wise, larger LLMs do not give better features. With our interface, the same LLMs improve steadily with size. TILE (Table-Interfaced LLM Embeddings) combines four ingredients: row serialization to provide cross-column context, intermediate-layer extraction to avoid layers specialized for next-token prediction, columnar pooling to remove mean pooling's length bias, and by-pass features to route numbers and categories past the LLM. Paired with TFMs, TILE sets a new state of the art for tables with strings. Across 100 datasets, it beats the strongest baseline on 89% of splits, with gains across 7 LLMs and 10 tabular learners, and ranks first on the 108-dataset STRABLE benchmark.

Abstract: Learning a response law for continuous decisions from observational time series is central to many real-world decision systems, yet temporal non-stationarity poses a fundamental challenge: as outcomes drift over time, naively pooled models can conflate action effects with shifting baselines and even reverse action rankings. Even when the one-step response is identifiable, unrestricted cross-time generalization remains fundamentally ill-posed. We therefore seek the part of the response that remains stable for decisions even when outcome levels do not. We propose deployable causal action geometry: the action-response shape that remains after anchoring away action-independent level shifts on a selected link scale and profiling out positive amplitude variation. Building on this target, we develop a two-stage orthogonal estimator that first obtains cross-fitted pilot estimates of anchored responses and then performs honest profiled selection over link, representation, and shape classes. The resulting estimator admits oracle guarantees for the restricted target and, under approximate persistence, produces decision rules that remain near optimal in future periods. Experiments on synthetic data and Dominick's support the proposed target and its transfer behavior. In a randomized Taobao A/B test, the deployed system improves GMV and purchase counts by \(1.16\%\) and \(1.70\%\).

Abstract: Financial candlestick understanding requires locating visual elements, aligning them across trading dates and panels, and combining observations through numerical and financial reasoning. Answer accuracy alone does not reveal whether predictions are supported by chart evidence. We introduce Code-Interactive Financial Candlestick Reasoning and present Fin-Thinker, a model based on Qwen3.5-9B that generates and executes code to acquire evidence and perform computations. The model uses the returned observations to guide subsequent reasoning. To train these capabilities, we construct FinKLine-32K with 32,184 replay-verified code-observation trajectories collected through teacher-guided student exploration. These include successful solutions with and without error recovery. Our three-stage training framework combines foundational visual-code fine-tuning, financial process supervision of successful reasoning and corrective continuations, and execution-feedback reinforcement learning. For evaluation, we introduce FinKLineBench with 1,200 questions across 138 financial task types to assess answer correctness, code execution, and evidence grounding separately. On FinKLineBench, Fin-Thinker improves strict accuracy by 13.1 and 33.2 percentage points over the best-performing direct-answer baseline among those evaluated and its base model with sandbox access, respectively. Training-stage ablations further show that financial process supervision and execution-feedback reinforcement learning yield successive improvements in both answer accuracy and GPT-5.6-judged grounded accuracy.

Abstract: LLM-powered data analytics aims to translate natural language instructions into executable analytical programs over underlying data. However, existing approaches, whether treating LLMs as intent-to-code translators or as standalone analytical engines, often fail to reliably align domain semantics with complex schemas and heterogeneous metadata, resulting in brittle execution and semantically inconsistent analytical outputs in real-world workloads. We present LYNX, a multi-agent framework that formulates LLM-driven analytics as a schema- and knowledge-constrained analysis problem rather than a single-pass generation task. LYNX organizes analytical synthesis into a closed-loop workflow of planning, generation, verification, and refinement through three role-specialized agents that collaboratively enforce schema grounding, semantic consistency, and execution correctness. To address domain ambiguity and schema misalignment, LYNX integrates Semantic-Structural Distillation and Stage-Aware Allocation (SSD-SAA). A delta-guided iterative revision continuously diagnoses and repairs semantic and execution-level failures, substantially improving synthesis robustness. We evaluate LYNX on two NL-to-SQL benchmarks, BIRD-SQL Mini-Dev and the more challenging Spider 2.0-Lite. Experimental results demonstrate strong performance and efficiency, achieving 10.66% to 59.54% execution accuracy across lightweight and commercial models, while reducing token consumption by 70.53% compared with the prior most efficient method. Our framework displays high generalization over different backbones, from open-source, lightweight models to the latest commercial models. Additional case studies on quantitative finance analytics and complex multi-relational SQL workloads further demonstrate the framework's robustness, scalability, and practical applicability in real-world analytical scenarios.

Abstract: We changed the agent: did it actually get better? Every self-improving agent loop answers this hundreds of times, and every answer comes from a verifier. On open-ended tasks none exists, so the loop is handed a hand-written rubric or a bare LLM judge grading output from a model like itself, inviting reward hacking and shared blind spots. We make the verifier the evolving object: an inspectable expression over small, mostly deterministic drawback detectors, synthesized from clustered failures, gated at birth, and selected for agreement with a ten-item anchored reference set plus consensus over unlabeled outputs, never for the agent's score. On MBPP+ it gains +0.21 held-out agreement over the hand-authored seed composition, on every seed, and ends ahead of the bare LLM judge it contains. One finding should change how co-evolved verifiers are validated: removing the anchor guards collapses the verifier into a vacuous always-pass grader, yet that collapsed verifier trains skills just as well. Downstream task score cannot certify a self-evolved verifier. Score does answer sufficiency, and there an evolved verifier can substitute: Double Ratchet, pairing the verifier with a lifecycle-managed skill loop, retains 88-110% of the lift that ground truth or a rubric buys the same loop, across code generation, enterprise text-to-SQL, and reference-free report generation. When evolved skills gamed the report rubric, an outer judge caught it and one added detector repaired it; the judge itself was wrong until given the task contract.

Abstract: Exploratory data analysis (EDA) is rarely open-ended in practice: analysts work from high-level domain questions toward the concrete analyses that can answer them, prioritizing directions with domain knowledge and prior hypotheses. Large language models (LLMs) can supply such knowledge, but their responses are unstructured, leaving analysts no way to see what has been explored, what is missing, or why one direction was chosen over another. We present DAG-EDA, a system that lets analysts and an LLM co-navigate the space of possible analyses through two linked structures. An intent graph, governed by a grammar of analytical intent, decomposes an ambiguous natural-language question into progressively concrete analysis tasks, keeping alternative framings open and letting analysts branch, backtrack, and compare paths. A multi-layered knowledge graph externalizes the LLM's domain knowledge, linking domain concepts to the dataset variables that can measure them, so analysts can inspect and contest how their question is grounded in the data. Both graphs are constructed from only the dataset and the analyst's question, and the analyses the analyst reaches are rendered as interactive dashboards. We illustrate the system through a usage scenario and describe a user study design for examining whether the system scaffold analysts' reasoning and navigation.

Abstract: Tabular foundation models (TFMs) are pretrained across diverse tabular tasks and make predictions on a new table at inference time using its labeled examples as context. Most recent TFMs perform such in-context prediction with stacked Transformer layers, repeatedly transforming how examples are represented and compared. By tracing individual queries through several strong TFMs, we find that predictive refinement is highly uneven across depth and is often concentrated in later layers. This uneven refinement motivates us to reconsider how intermediate representations are constructed and reused throughout the network. We introduce Retro, a tabular foundation model based on retrospective inference, where later stages can explicitly revisit and recombine intermediate information produced earlier in the network. Retro organizes this process around two complementary operations: which intermediate information to revisit, and how the resulting contextual update should be shaped for each query. Attention Residuals address the former by adaptively reweighting contributions from different depths, while query-conditioned Gated Attention addresses the latter by modulating the attention output element-wise across representation dimensions. Our analysis shows that Retro shifts predictive refinement earlier and more broadly across depth, with different stages revising different subsets of queries in a pattern suggestive of multi-view refinement. Across TabArena, TALENT, and RelArena, Retro ranks among the top three and lies on the Pareto frontier. These results indicate that directly reusing intermediate representations provides a practical way to better exploit depth in TFMs.

Abstract: While Large Language Models (LLMs) possess rich world knowledge and impressive generalization capabilities, their direct application to tabular data classification is hindered by high inference costs and limited interpretability. In contrast, decision trees are fast and transparent but often underperform in low-data regimes. In this work, we propose a novel framework that bridges these paradigms by distilling LLM knowledge into interpretable decision trees under a few-shot learning setting. Instead of directly prompting the LLM to generate full trees, which is often unstable and inefficient, we develop a three-stage paradigm that prompts the LLM to generate rules and organize the rules into a tree. Experiments on multiple real-world tabular datasets demonstrate that our method achieves superior accuracy and interpretability with significantly lower prompting overhead compared to existing baselines.

Abstract: In the era of interconnected data, graphs have emerged as an effective abstraction for modeling complex systems in an intuitive format, especially with the rise of Property Graphs, which offer an intuitive and scalable way of navigating non-intuitive structures. In this context, graph mining techniques have been developed for testing complex graph-based rules, as the MINE GRAPH RULE operator, which, however, require users to have prior expertise both in graph theory and formal query language. In this work, we propose to bridge the gap between users and the graph-association rule-mining process by showing how Large Language Models (LLMs) can be easily prompted to formulate, refine, and interpret complex relational rules, directly producing MINE GRAPH RULE queries.

Abstract: Visualization dashboards are widely used interactive tools, but a disconnect exists between the dynamic data they display and their static structure. End-users cannot modify the dashboard to answer new questions. We introduce Living Dashboards, whose views are born, wither, revive, and die in response to how they are used. Rather than requiring manual reconfiguration, a living dashboard observes interaction and natural-language queries to autonomously wither neglected views and revive those used again. More consequential decisions, such as adding or retiring views, are deferred to the user. We formalize the concept as a four-dimensional design space and implement it in Living Dashboard, a web-based prototype. We evaluate it in an exploratory between-subjects study (N = 12) against an AI-supported baseline on analytical tasks. Living Dashboard participants answered more tasks correctly, reported lower workload, and rated the system higher on usability, though the two conditions differed in more than adaptive behavior alone.

Abstract: Real-world reasoning rarely reduces to static question answering: agents must actively gather information from tools and sensors that are often noisy and unreliable. Yet most existing active reasoning benchmarks assume that environmental feedback is trustworthy, or introduce noise without exposing an explicit, calibrated uncertainty signal, leaving open how LLMs should reason when the evidence itself is uncertain. We introduce VisualNoiseQA, a novel benchmark for active reasoning under noisy visual feedback. A text-only LLM must solve VQA problems by iteratively querying a fixed, off-the-shelf VLM treated as a stochastic visual sensor. For each query, we draw multiple samples and expose an empirical uncertainty signal via self-consistency, enabling the reasoner to probe from different angles and decide what to ask next and when to stop. Our construction is automatic and scalable: starting from diverse VQA sources and two noisy VLMs, we retain only questions where the sensor is inconsistent yet human-solvable. We evaluate multiple LLM reasoners on 1,000 instances spanning perception, chart understanding, and knowledge-intensive reasoning. VisualNoiseQA thus provides a controlled playground to study how different LLMs exploit uncertainty signals for robust reasoning.

Abstract: Recent advancements in large language models have introduced new capabilities for reasoning over structured data, particularly through program-aided tools that can analyze tables. However, many existing methods address single-table scenarios or assume that the relevant tables are already provided. In practice, users often issue complex data exploration queries over entire databases, where relevant information may be distributed across multiple relations. In this work, we introduce DBRAG, a retrieval-augmented generation framework tailored for multi-table question answering. DBRAG first retrieves candidate tables using an offline table index, enriches their summaries with query-relevant rows, and uses an LLM to rerank the candidates. A program-aided reasoner then selects the required tables and executes operations over their full contents, keeping the initial prompt context compact. Experiments on the Spider, GeoQuery, and ATIS datasets used in this study demonstrate improvements in table retrieval and multi-table question answering.

Abstract: LLM agents rely on long-term memory to retain and reuse information when performing tasks over long horizons. Existing methods provide limited support for handling memories that become outdated as new observations or domain evidence arrive. Such outdated memories may remain semantically relevant, continue to affect dependent records, and retain value as historical evidence. This calls for two capabilities: dependency tracking to identify downstream effects and historical preservation to retain useful past records. We propose Provenance-Aware Cascading Memory Invalidation (PACMI), a framework that represents memories and new evidence in a provenance graph with typed dependency edges. PACMI assigns records to a four-state validity lattice, propagates validity changes to dependent memories, and uses the resulting states for retrieval and stale-premise detection. We also introduce a diagnostic benchmark with 100 cases and 300 queries across five domains. The evaluation separates node, context-, and answer-level performance. PACMI achieves the highest final-answer accuracy on this benchmark, and its paired difference from the strongest baseline is significant under an exact McNemar test. The premise checker achieves perfect precision, recall, and F 1 on the controlled query distribution. Cascading propagation primarily improves memorystate correctness: removing it increases final-answer errors from 3 to 11, but the paired difference does not reach the 0.05 significance threshold. Code and data will be made publicly available.

Abstract: Improved name retrieval may have little effect on company clusters when the pair classifier remains unchanged. We examine this dependency by adapting multilingual E5 encoders under fixed candidate budgets and downstream decision rules. Random-negative and hard-negative training use identical positive schedules. Checkpoints are selected before collecting a new GLEIF sample of 3,633 names, 2,880 source identities and 882 silver-positive pairs. At 72,660 candidate edges, adaptation with a multi-view selector increases direct pair recall from 53.74% to 76.98%. The primary matcher adds only seven correct and two incorrect co-cluster pairs: cluster recall rises from 32.54% to 33.33%, while precision falls from 95.99% to 95.45%. Of 208 newly retrieved silver-positive pairs, 202 fall below its decision threshold. Random-negative and hard-negative training produce identical final partitions. An AI-assisted, single-reviewer audit of 137 pairs supports the observed pattern, although its predominantly LEI-derived evidence does not establish independent gold labels. The results locate the immediate loss of retrieval gains at the existing confirmation stage and show why encoder evaluation must also measure final cluster quality.

Abstract: SQL queries that large language models write from natural language questions can execute successfully yet produce incorrect results, so execution alone does not reveal what to fix. An error taxonomy says why the query is wrong, but not where to look or how to change it. Existing methods can guide SQL correction through feedback, error reports, or generated plans alongside an unmasked query. We introduce TEG(Taxonomy-guided Error Grounding), which turns a supplied diagnosis into a structured correction input for natural language-to-SQL (NL2SQL) correction. Type-specific rules map each error type to construct classes to reconsider and an edit operation to request. TEG masks the selected constructs in the query when applicable and states that operation in an edit instruction. TEG generates candidate corrections from this input, uses execution feedback to guide candidate selection, and repeats the process one annotation at a time for queries with several errors. On NL2SQL-BUGs, TEG reaches 47.3 single-error execution accuracy and 37.0 overall with Qwen2.5-7B-Instruct. Across the model sizes and thinking modes evaluated in the main comparison, TEG outperforms all evaluated baselines on single-error queries, even when the baselines receive the same error-type annotations. With predicted types, TEG stays above direct LLM correction and ErrorLLM on single-error queries.

Abstract: Many inference workloads evaluate a trained tree ensemble on row groups that share feature values: discrete-time survival models expand each patient into $G$ time steps, click-through-rate models score every item in a search session, and scenario analyses vary a few inputs while holding the rest fixed. Standard inference treats each row independently and repeats the shared work $G$ times. We present TreeWalker, which applies partial evaluation to grouped inference: constant features are static, varying features dynamic. It walks each tree once per group, partitions a row bitmask at varying splits, and skips empty subtrees. Training is unchanged: TreeWalker reads standard LightGBM and XGBoost models. We prove a structural work decomposition: per-tree work splits into the constant-projected subtree size $|T_c|$, $G$ leaf writes, and a predicate-mask provisioning cost $Q$. For the trace evaluator, per-row work approaches a $(d_v+1)/(d+1)$ fraction of a row-independent walk as $G \to \infty$. On Intel, TreeWalker is 2.5-3.2$\times$ faster than a row-independent traversal at the reference configuration ($T=500$, $L=8$) and 6.8-7.8$\times$ faster at $G=128$ on the survival datasets, with larger gains on Arm. On a scenario-analysis benchmark it is faster in all 16 configurations on both architectures. For f64 models, outputs match treelite's GTIL up to summation order; for f32 models, f64 accumulation is closer to a Kahan-compensated reference than native f32 on 99.98% of rows and never farther.

Abstract: Table-to-report generation refers to the task of automatically generating article-level analyt- ical reports from relational tables and is an essential capability for automated data science and decision support. Its central challenge lies in systematically discovering verifiable com- posite insights across tables, attributes, and analytical perspectives, and organizing them into coherent, complete, and traceable evidence chains. Existing methods primarily rely on sequential, reactive data agents or direct Large Language Model(LLM) generation. They suffer from exploration bias: early local observations constrain subsequent actions, causing models to focus prematurely on local analyzes and miss cross-table or cross-dimensional evidence. We propose ComInsight, which reformulates insight discovery as the composition of atomic evidences. We first define an atomic insight as the smallest executable analytical unit conforming to a predefined analysis pattern and enumerate all valid atomic insights from database schema and content. These atoms are then organized into a multi-relational insight graph, where nodes represent verified data facts and edges encode logical, temporal, or hierarchical relations. Finally, a set of composition operators systematically fuses atomic nodes into higher-order composite conclusions. Every composite output is accompanied by executable SQL and fine-grained provenance, ensuring full verifiability. Across three benchmarks InsightBench, DDR-Bench, and T2R-Bench, ComInsight consistently outperforms strong baselines in factual correctness, novelty, and structural completeness. We believe ComInsight offers a reliable, efficient, and explainable path toward table-to-report generation.

Abstract: General-purpose Text-to-SQL systems achieve strong performance on academic benchmarks like Spider and BIRD, where schemas are relatively shallow and column values are often human readable. In production financial databases, where concepts are stored as opaque integer keys rather than human-readable strings, these methods fall below 50%, as even simple queries require multiple joins and filter predicates reference opaque IDs. We present Financial LINking Text-to-SQL (FLINT), a domain-specialized Text-to-SQL system that closes this gap through three key components: (1) a lookup agent that dynamically resolves natural-language concepts to question-specific reference table constraints, (2) embedding-based retrieval of structurally similar query templates from a compact, expert-authored bank, and (3) schema linking that prunes a large table schema to the relevant subset by traversing foreign-key chains, rather than relying on name similarity alone. We evaluate on two datasets totaling 359 questions over production financial schemas. FLINT outperforms various state-of-the-art baselines using the same LLM. The system is deployed in production as part of a financial data retrieval service.

Abstract: Tabular foundation models achieve state-of-the-art performance on single-table tasks without any training. Recent work suggests that they are also well-suited for relational learning via deep feature synthesis (DFS), which flattens a relational schema into a single table by adding aggregates of the other tables' columns as features. This approach is appealing because it directly benefits from improvements to or customization of the underlying tabular foundation model. In this paper, we identify two key problems with DFS: feature explosion and interaction blindness. The first problem arises because the number of DFS features grows quickly as the schema becomes more complex, limiting scalability and performance. The second problem arises because column-wise aggregates do not account for feature interactions, limiting performance. We propose and explore an alternative method termed RelICL, which keeps the benefits of DFS but alleviates these two problems. At its heart, RelICL propagates and fuses information step by step through the schema graph, using the same tabular foundation model that is eventually used for prediction to do so. In our experimental study using RelBench tasks, RelICL was on par with the strongest approach based on deep feature synthesis.

Abstract: Data lakes contain a plethora of attributes scattered across many tables that, when combined, provide enhanced assets for data analysis. Nonetheless, deciding which attributes belong together in meaningful relations remains a manual, per-task effort. Merging by joinability alone provides no guarantees regarding attribute relevance, while selecting features against a single target discards attributes useful to other tasks. To address this gap, we introduce the data composition problem: organizing a fragmented, heterogeneous lake into meaningful relations, agnostic of any particular analytical task so that the resulting organization can serve as a common foundation for diverse downstream analyses. We propose DIADA, a composition system that employs multivariate dependence as the criterion for assessing the meaningfulness of a relation and approximates it by hypothesizing independence among attributes and identifying those sets that violate this hypothesis. To do so, we map the attributes to a predicate space, forming a lattice under inclusion and mining those predicate sets that exhibit dependence among their constituents. We contribute a dedicated and scalable algorithm to effectively explore this space, outscaling classical algorithms for mining relationships, thus discovering dependencies that would otherwise be impractical to identify. We demonstrate that applying a single data composition process benefits diverse potential downstream tasks. This is the result of providing a subset of low-noise, statistically relevant attributes that increases the confidence that detected patterns are grounded in real relationships, thus preventing common modeling issues in large-scale environments.

Abstract: Real-world time series forecasting systems operate under non-stationary data streams, where forecasting performance may degrade over time. Although retraining can recover the performance, it incurs non-trivial computational and operational costs. Under limited deployment resources, the key challenge is therefore not only how to retrain but also when to retrain. While existing retraining policies often rely on indirect indicators such as drift alarms or model staleness, we instead use realized forecast errors as direct deployment feedback. In this paper, we propose PILOT (Pseudo-label-Informed Learned Online Trigger), an online retraining framework that learns when to retrain from forecast-error dynamics. Since ground-truth retraining labels are unavailable, PILOT constructs a pseudo-label from future increases in forecast error and trains a lightweight scorer to predict it from observed error states. At deployment, PILOT uses only completed forecast errors and serves as a plug-in module for arbitrary forecasting backbones without architectural modification. We evaluate PILOT under standard multivariate forecasting settings across eight benchmarks with three representative backbones---DLinear, iTransformer, and TimesNet. Across all three backbones, PILOT achieves state-of-the-art average-rank performance among retraining policies while maintaining a favorable performance--efficiency trade-off.

Abstract: A large class of data-centric tasks is exploratory, where users iteratively steer workflows, refining subjective goals as new insights emerge. These Exploratory Data Tasks (EDTs) are performed by millions of users with varying levels of expertise to understand unfamiliar data, discover trends, and identify evidence that informs critical decision-making. However, a key challenge in EDTs is the enormous space of possible actions that one can take at each step: users struggle to choose among thousands of joins, transformations, and aggregations, causing "exploration paralysis". Because EDT workflows are interconnected, each choice impacts subsequent exploration, and suboptimal choices can lead to inefficiency, missed insights, confirmation bias, and incomplete coverage. This calls for intelligent recommendations that efficiently guide users toward optimal EDT actions. We envision recommendation as a core capability of data systems, proactively guiding users toward promising actions and thereby lowering the barrier to exploratory data tasks. EDT recommendation is challenging because the action space is combinatorial and actions are data-dependent, which require costly materialization. Moreover, recommendation often involves bundles or sequences of actions across interdependent tasks, requiring coordination across tasks. In this paper, we present our vision of EDT recommendation systems along two axes: single-task vs. multi-task settings and single-action vs. multi-action recommendations. We outline a research agenda that progresses from recommending individual EDT actions to constrained bundles and sequences of actions, and ultimately to coordinated recommendations across interconnected EDTs. We identify research directions for incorporating various contexts (user, data, task, and ecosystem), addressing efficiency challenges, and coordinating across tasks.

Abstract: Reliable infographic generation requires facts, symbols, and visual relations to remain consistent through rendering and revision. Correcting one element also requires tracking its supporting evidence and the dependencies affected by the change. We present \textbf{InfoAgent}, a training-free framework for \emph{evidence-bound visual-symbolic program synthesis}. Its Infographic Visual Description (IVD) records factual payloads, evidence provenance, execution routes, and verification obligations in a typed dependency graph. Retrieved design priors guide compilation, and layered execution combines raster synthesis with editable symbolic and binding objects while retaining their traces. Dependency-aware repair localizes corrections, rechecks affected dependencies, and requires protected obligations to remain satisfied under the declared checkers. Unresolved obligations remain explicit. On IGenBench, InfoAgent achieves 93.0 Q-ACC and 59.0 I-ACC. We also introduce InfoGraphicBench-Evidence, where complete-checklist pass rates on 200 test requests increase from 21.5\% for Same-IVD Prompt to 23.5\% for the initial layered output and 28.5\% after repair, using the same evidence and initial IVD. On 120 audited repair cases, localized repair edits 12.4\% of the canvas on average, compared with 67.3\% for global regeneration.

Abstract: LLM-based agents increasingly collaborate with users on long-horizon tasks, accumulating evidence, code, and drafts through extensive search, reasoning, and execution. As users inspect these results, they may supply missing information requirement completion, introduce new requirements requirement elicitation, or revise existing ones requirement shift. These changes often affect only part of the accumulated work, yet agents may carry forward obsolete information or turn local revisions into global rewrites. Existing approaches clarify current intent without determining how prior work should change, or reuse execution histories under a fixed objective. We address this gap by formulating dynamic-requirement collaboration as joint requirement tracking and local update. We introduce GitHarness, a pluggable Git-style framework that organizes requirement states and their corresponding harness work states into a branchable version history. A trainable Git Agent resolves requirement changes and selects a semantically compatible historical state. A unified version interface then restores that state and creates a new branch, enabling the underlying harness to exclude obsolete information, inherit compatible work, and focus execution on affected parts. The Git Agent is trained through interface-level black-box reinforcement learning, with downstream harnesses and task-execution models kept fixed. We also construct MTAgentBench, a verifier-preserving benchmark covering mathematical reasoning, text-to-SQL, agentic search, software engineering, and research synthesis. Experiments demonstrate strong task performance alongside effective requirement tracking, preservation of valid work, and efficient execution.

Abstract: Multi-view clustering aims to capture cross-view consistency while exploiting view-specific information. However, shared representations learned to capture cross-view consistency may still retain view-identifying information, potentially compromising the consistency of cross-view clustering structures. To address this issue, we propose ACGRL, an adversarial consistency-guided representation learning framework for multi-view clustering. ACGRL employs a gradient-reversal view discriminator to reduce view identifiability and obtain invariant reference representations. These representations are then frozen to provide fixed references for disentangling view-specific information from cross-view common information in the subsequent learning stage. The fixed reference representations are concatenated with the learned view-specific representations for reconstruction and clustering, with cross-view cluster alignment encouraging consistent clustering assignments. Experiments on four benchmark datasets demonstrate the superior clustering performance of ACGRL compared with representative multi-view clustering methods.

Abstract: Generative AI promises easier dashboard creation, raising questions about the future of dashboards and the people who create and use them. We interviewed 16 experts based in 14 countries about their practices and expectations. Almost all expected dashboards to persist for recurring questions, monitoring, and reporting. They anticipated adaptive views and combinations of language, graphical controls, and gestures, while emphasizing interaction as part of human exploration and understanding. Participants expected authors' responsibilities to shift toward specifying requirements, curating generated work, and evaluating outputs, with design knowledge and communication remaining important. Easier creation also raised concerns about validation effort, users' understanding, maintenance, and personalization weakening shared understanding. We discuss seven opportunities for research and practice concerning validation, end-user education, dashboard proliferation and rot, organizational guidance, adaptation, novel visualizations, and accountability for AI-generated content. Our findings connect dashboard evolution with the human and organizational work needed to sustain their use.

Abstract: Large language models (LLMs) have significantly advanced natural language querying over relational databases, yet their ability to query time-series databases (TSDBs) remains largely unassessed. Existing benchmarks fail to adequately capture the non-unified query syntaxes, diverse application domains, and unique time-specific query intents inherent to TSDBs. To address this gap, we introduce TQTS-BENCH, a multi-syntax benchmark for evaluating text-to-query capabilities over TSDBs. TQTS-BENCH contains 6,125 high-quality question-answering (QA) pairs spanning 97 TSDBs, 23 distinct query syntaxes, 22 application domains, and 4 types of time-specific query intents. It is constructed through a human-centric AI-assisted workflow, where all QA pairs are carefully reviewed and revised by domain experts to ensure quality and correctness. Extensive evaluations of advanced LLMs and state-of-the-art text-to-query methods reveal challenges in querying TSDBs. Even the best-performing model evaluated, Claude-Opus-5, achieves only 48.98% execution accuracy, while humans reach 87.34%. Error analysis reveals that this performance gap mainly stems from the heterogeneous query syntaxes across different TSDBs, misinterpretation of time-specific intents, and incorrect schema linking. These findings highlight new opportunities to narrow the gap between current LLM capabilities and the requirements of TSDB queries in real-world applications. The benchmark is available at: https://anonymous.4open.science/r/TQTS-Bench-00CD.

Abstract: Evaluating statistical discovery by large language model (LLM) agents requires verifiable analytical ground truth. Establishing such ground truth for real-world datasets is costly, and prior knowledge of public datasets can influence agent responses. We introduce SLEUTHBENCH, a benchmark that addresses both problems by injecting controlled data-quality problems and feature effects into public tabular datasets: the injected pattern determines the answer, so reference answers are computed automatically and memorized knowledge of the original table is insufficient, while the table keeps its background structure. The injected patterns are modeled on phenomena reported in real data analyses. The benchmark defines 17 question templates in two families: data-quality questions and feature-contribution questions. We evaluate six state-of-the-art LLMs that analyze the data using a Python coding tool, on data-science and business phrasings of 70 validated dataset-template combinations, yielding 1680 graded responses in total. The models detect data-quality problems reliably (83.8% accuracy) but recover feature contributions poorly (41.9%). Finding how features shape the target requires searching over both candidate variables and analytical procedures. To address this issue, we propose the Empirical Layer, a set of precomputed statistical artifacts comprising summaries, fitted feature and interaction effects, and dataset descriptions, which exposes candidate patterns for direct inspection. Access to these artifacts raises feature-contribution accuracy from 41.9% to 68.0%.

Abstract: Open-domain table retrieval seeks tables that contain sufficient evidence for answering a question or verifying a claim. Yet semantic relevance is often misleading: topically similar tables may lack the required facts, while answer-bearing evidence is often confined to a few cells whose meaning depends on surrounding schema and table context. Heterogeneous schemas, value formats, and serializations further weaken one-shot matching. We present TableSeek, a structure-preserving agentic search framework for heterogeneous table corpora. Instead of ranking tables once, an LLM agent iteratively follows sparse clues, inspects schema-preserving previews, identifies schema- and value-level mismatches, and refines its investigation. TableSeek uses cells and schemas as evidence anchors while retaining complete tables as evidence units, enabling fine-grained localization without losing the context required for interpretation and answerability checking. Without relying on retriever training or a precomputed semantic index, TableSeek produces transparent evidence-seeking trajectories and achieves competitive end-to-end performance against strong retrieval-and-reranking pipelines on heterogeneous table benchmarks. These results suggest that active, structure-preserving evidence seeking is a promising paradigm for open-domain table retrieval.

Abstract: Adapting general-purpose multimodal large language models (MLLMs) to specialized domains requires learning domain-specific decision criteria, which often hinge on subtle visual distinctions between otherwise plausible answers. Rationale augmentation aims to expose such evidence through additional observations or inter-sample comparisons, yet a visually valid cue is not necessarily decision-relevant: it may describe how samples differ without changing the model's relative preference between competing answers. We therefore introduce BIRD, a self-improving Boundary-Informed Rationale Distillation framework that uses model-specific confusions to locate unresolved local decision boundaries and distills the evidence that resolves these confusions into rationales. For each sample, BIRD retrieves candidate neighbors from the target MLLM's own representation space and selects the most confusable one according to its answer preferences. It then generates answer-blind candidate evidence from their visual differences and functionally verifies which evidence most effectively strengthens the model's preference for the correct answer while avoiding inappropriate transfer across the pair. The verified evidence is then distilled into a single-sample rationale for standard supervised fine-tuning. Experiments on medical and chart VQA show that BIRD outperforms competing rationale-augmentation methods across two target MLLMs, while further analyses demonstrate clearer separation of confusable answers and stronger gains from model-matched supervision.

Abstract: Large language models (LLMs) are enticing in their promise to support data visualization (Vis) through faster and simpler workflows for data prep, analysis, and visualization creation. Yet LLMs are notoriously error-prone and not built for data visualization tasks. Few studies have explored LLM adoption among Vis practitioners. To fill this gap, we conducted semi-structured interviews with members of the Data Visualization Society, a global community of data visualization designers. Our findings show that Vis designers actively use LLMs for both creative and technical aspects of the visualization process. A new visualization workflow is emerging, a process we call vibe analysis, analogous to vibe coding. Some key challenges raised by participants parallel those of vibe coding, while others are Vis-specific, like gaps in Vis knowledge and chart verification. This work opens up opportunities for research combining LLM-mediated work with Vis tools that incorporate data visualization guidance, constraints, and best practices.

Abstract: Temporal knowledge graph forecasting aims to infer future relational facts from the temporal structure of observed events. Existing forecasters mainly summarize history through entity states, relation states, paths, or exact recurrence. These views often miss pair-specific transition evidence, that is, the way prior relations between the query actor and a candidate change the odds of the target relation. We introduce BridgeMem, which estimates this quantity as a residual added to the log scores of a frozen full-vocabulary forecaster. For each candidate, BridgeMem retrieves the pair's events that strictly precede t, encodes their relations, directions, and lags, and converts them into a likelihood-ratio correction. A support-adaptive empirical-Bayes reader trusts exact transition counts where they are abundant and backs off to a learned attention estimator where they are sparse. The backbone's own uncertainty gates the correction, so confident queries and candidates without dyadic history are left unchanged. On five benchmarks, BridgeMem improves on the strongest of nine baselines from 2021--2026 in all 20 filtered MRR and Hits@{1,3,10} comparisons, with MRR gains of 0.0213, 0.0164, 0.0216, 0.0112, and 0.0028 over the best prior result. These results show the value of explicit dyadic transition modeling.

Abstract: Causal inference guides operational and managerial decisions but remains challenging in high-dimensional panel or tensor settings, where decisions may depend on the joint conditional distribution of missing control outcomes. We develop \emph{Counterfactual Tucker Diffusion} (\CFTDiff), which integrates the treatment mask and latent Tucker structure into conditional diffusion to recover this distribution given observed control outcomes through efficient nonlinear score learning in a low-dimensional core. The masked Tucker score preserves dependence across tensor modes while reducing the dimension of nonlinear score learning from the product of mode dimensions to the much smaller product of Tucker ranks. We establish high-probability error bounds for conditional score estimation that depend on the Tucker ranks, largest mode dimension, and the factor-strength-adjusted number of missing outcomes, and show how these bounds translate into recovery guaranties for the conditional distribution of the missing control outcomes. Across missing rates, simulations show more accurate point recovery than common causal panel and matrix/tensor completion methods; comparisons with nested diffusion specifications further demonstrate the gains from masked conditioning and Tucker dimension reduction. In Norway's iFlex experiment, \CFTDiff recovers missing outcomes more accurately than competing methods; when applied to causal analysis, its estimated conditional distributions yield counterfactual prediction intervals and target-attainment probabilities, allowing pricing interventions to be evaluated by demand-reduction magnitude and reliability.

Abstract: Structured-data agents in enterprise settings must reason over complex data environments whose relevant evidence is distributed across schemas, relationships, policies, and recurring business roles. Modern agentic systems often address this burden through reusable markdown-style memory or skill files that preserve previously discovered information for later queries, reducing the need to rediscover the same structure repeatedly. This is useful, but it obscures a natural division of labor: agents are well suited to semantic reasoning, while learned systems are well suited to predicting and organizing recurring structure. We introduce latent equivalence learning to bridge this gap. The framework separates persistent task-relevant identities from their dataset-relative realizations. In our realization, supporting and opposing evidence shape support-realized Gaussian prototypes that learn how those identities are expressed in a particular data environment, while soft-membership profiles retain distinctions lost under a hard assignment. A separate learned query-prototype system represents recurring evidential requirements and maps them through a learned compatibility function into the same persistent identity structure. This identity-factorized, query-conditioned routing materializes the relevant dataset-specific evidence for downstream reasoning, allowing the agent to operate over an already organized evidential state rather than reconstructing cross-schema structure at every query. On the Data Agent Benchmark, spanning 54 queries across 12 heterogeneous datasets, our full implementation achieves 94.67% dataset-macro stratified Pass@1 over five complete trials and 258/270 successful raw query attempts, compared with 55.51% for the benchmark's Claude Opus 4.6 reference agent, ranking first among 40 leaderboard entries at submission.

Abstract: Legends are fundamental to chart understanding, as reliable interpretation requires correctly binding legend entries to corresponding visual marks. While vision-language models (VLMs) are increasingly applied to chart understanding, their legend understanding is poorly diagnosed by aggregate accuracy, which can be satisfied by superficial shortcuts and confound legend-specific errors with other reasoning failures. To enable fine-grained diagnosis and controlled testing, we introduce LegendBench, a parametric benchmark and generation pipeline that produces targeted legend-centric test cases. LegendBench contributes (1) a capability-task taxonomy spanning legend parsing, legend grounding, legend-conditioned reasoning, and legend-aware abstention to localize failures, and (2) counterfactual group generation, where each base chart yields multiple variants under controlled legend interventions to probe model invariance and sensitivity. Using LegendBench, we evaluate both general-purpose VLMs and specialized chart models and generate their capability profiles, revealing persistent bottlenecks in reliable legend-to-mark binding and counterfactual consistency. We then use these capability profiles to guide targeted fine-tuning, demonstrating that bottleneck-specific interventions can effectively close the localized capability gaps and generalize to unseen data. We further leverage our counterfactual design to conduct fine-grained diagnostic experiments, analyzing encoding-channel effects, legend-order shortcuts, and abstention under varying visibility.

Abstract: Traditional data systems face profound limitations in the AI era, relying on human-crafted pipelines, lacking semantic understanding of heterogeneous data, and operating through rigid, reactive processing. To address these challenges, we propose a new paradigm called the Data Agent, designed to manage, process, and analyze data with minimal human intervention. Data agents autonomously execute a wide range of data-related tasks, transforming traditional data systems by shifting from manual design to autonomous orchestration, from literal manipulation to semantic interpretation, and from reactive to proactive processing. Our Data Agent system includes six components: semantic data organization, semantic operators, agentic pipeline orchestration and optimization, feedback-driven refinement, memory management, and proactive adaptation. Building on this foundation, we also develop two specialized agents: the data analytics agent and the data science agent. Experiments on real benchmarks demonstrate significant performance gains of our data agent over state-of-the-art methods. We identify open challenges to guide future research in building fully autonomous data systems.

Abstract: Visual analytics (VA) enables sensemaking through interactive visualization, but effective analysis often requires experts to translate high-level intents into long sequences of interface operations and iteratively interpret visual feedback. We study whether modern vision-language models (VLMs) can take on this role as autonomous VA operators that observe the interface, plan multi-step exploration, execute interactions, and adapt based on intermediate visual feedback. To support systematic development and evaluation, we first introduce WidgetVA, a widget-centric agentic VA framework that standardizes interactive components as structured widgets with unified action (e.g., filter and zoom) and perception-query (e.g., selection summaries) APIs. This standardization supports two modes of system construction: wrapping an existing VA system to make it agent-operable without rebuilding it, and composing a new system from widgets as modular building blocks. To help agents coordinate across widgets rather than plan each interaction from scratch, each widget further packages reusable analytical workflows, giving agents more than a bare set of callable functions to plan over. Building on this framework, we present WidgetVABench, a benchmark of single- and multi-widget VA tasks that require agents to perform multi-step interactions to uncover evidence and produce verifiable results. Each task also provides fine-grained reference annotations so that WidgetVABench can score Answer, Reference Trace Similarity, and State separately rather than collapsing agent performance into one success score. Experiments across multiple VLMs show that our framework provides an effective scaffold for agentic VA, while the diagnostic measures expose persistent limitations for future work. The WidgetVA framework and WidgetVABench have been released in https://github.com/Hiverwin/widgetva.

Abstract: Chart reasoning agents are increasingly used to extract actionable insights in critical domains, achieving state-of-the-art performance on multiple benchmarks. Yet, high benchmark accuracy alone is insufficient for deployment, where stakeholders must be able to audit and verify how a model reaches its answer. Existing LVLM-based chart agents produce either answer-only predictions or free-form rationales that are hard to verify, obscuring whether an error arose from misreading the chart, extracting a wrong value, or miscomputing. We propose Chart-RVR, a reinforcement learning framework for training monitorable chart agents with verifiable process rewards. Chart-RVR decomposes chart reasoning into three auditable blocks: Structure, identifying the chart type; Evidence, reconstructing the underlying data table in JSON; and Derivation, exposing the stepwise trace that computes the answer. Across six in-domain and out-of-domain benchmarks, Chart-RVR attains state-of-the-art accuracy among comparable-sized LVLMs. Beyond accuracy, we assess monitorability using a triangulated protocol that combines ground-truth surrogate metrics, an oracle information-gain measure, and an LLM-as-auditor scoring Process Verifiability and Evidence Localization, showing that Chart-RVR yields rationales that are markedly more verifiable and evidence-grounded than those from CoT prompting, SFT, and existing chart-specific baselines.

Abstract: We develop exponential family synthetic controls (EFSC), a distributional version of synthetic controls for a panel of datasets. Each cell of the panel corresponds to a dataset drawn from an exponential family whose natural parameters factorize probabilistically across units and times. We estimate the latent factors using black-box variational inference. This replaces the usual weighted-average view of synthetic controls with a flexible probabilistic model that operates on full distributions. We propose causal estimands based on divergences between pre- and post-intervention distributions induced by the posterior of the natural parameters, together with distributional placebo tests to support causal inference and assess the significance of the estimated effects. We validate the proposed framework on synthetic and real data. Across a variety of exponential-family distributions, EFSC accurately recovers causal effects induced by exponential tilts, together with the corresponding divergences between treated and counterfactual distributions. The framework also captures effects induced by structural perturbations of the latent factors and by heavy-tailed noise contamination. Finally, we apply EFSC to study the expansion of Medicaid under the Affordable Care Act (ACA) and its impact on the distribution of health insurance coverage across U.S. states. Code is available at https://github.com/blei-lab/efsc.

Abstract: LLMs can generate fluent descriptions from tables, but their outputs may remain logically unsupported by the structured data. We introduce STAT-TO-TEXT, a controlled task in which LLMs generate quantified natural language inferences from statistical tables using quantified constructions such as all, some, no, and most. To evaluate these inferences, we use an LLM generated Python checker code which when executed verifies the corresponding truth conditions against the table. We compare four open-weight LLMs across model families and scales, evaluating faithfulness, logical accuracy, table coverage, and diversity. Our results show that model scale and family matter, with the largest model (GPT-OSS-120B) consistently producing the most faithful inferences without sacrificing greater table coverage and quantifier diversity, as opposed to smaller models. These findings are supported by human annotation, which shows that the automated checker closely aligns with human judgments.

Abstract: Large language models (LLMs) have been applied to causal discovery, but candidate-graph generation rarely treats premature omission of potentially relevant causal relations as an explicit design objective. We propose MaSCoD, a multi-agent framework that organizes candidate third variables and local structural patterns before direct-edge judgment. We evaluate MaSCoD on Auto-MPG, DWD, and Sachs using GPT-5.4 as the primary backbone and GPT-4o for replication. MaSCoD exhibits a dataset- and backbone-dependent retention-selectivity profile rather than uniform superiority. Across all six dataset-backbone settings, Full, which supplies structural hypotheses before direct-edge judgment, achieved higher mean Recall and F1 than No Phase 1, which instead constructs them within the judgment procedure, while also increasing false-positive rates. Additional reference-edge retention over all evaluated baselines was observed on DWD with GPT-5.4 and on Sachs with GPT-4o, rather than uniformly across settings. Partial ablations showed that supplying both information components did not always outperform supplying only one. For GPT-5.4, stage-wise analysis showed that the Full-No Phase 1 retention gap was already present after direct-edge judgment, while reconciliation introduced additional reference-edge loss for Full on Sachs. These findings support structural pre-organization as an explicit design and evaluation target for omission control and motivate evaluating context construction jointly with its utilization in judgment.

Abstract: Tables are central to data work to support precise lookup and full detail, but they can be limiting for overview and pattern-finding tasks. Visualizations are then created to gain richer perceptual support. In practice, moving between tables and charts often requires maintaining parallel representations, introducing context switching, and extra coordination work. Building on prior hybrid table-visualization systems, we present MuTable, a prototype that reifies transformations as persistent, composable, and reusable modifiers to support in-situ data exploration. Users can reshape the table while retaining and adapting intermediate forms as their questions evolve. An expert interview with eight data workers suggests that MuTable can support coordination between representations, rapid exploration, and greater user agency in constructing visualizations, as a low-commitment exploration space.

Abstract: State-of-the-art Text-to-SQL systems are typically multi-agent pipelines centered around two fundamental tasks: schema linking and SQL generation. However, existing work trains separate models for each task, failing to leverage the synergy between these interrelated tasks. In this work, we propose DualSQL, a new Text-to-SQL system consisting of two agents powered by a single model backbone. The agents share the same model weights and agentic scaffold, enabling joint optimization through a robust multi-agent reinforcement learning (RL) framework. We design three database access tools to facilitate effective multi-step reasoning grounded to interactions with the databases. To improve training and avoid model collapse, we introduce a set of rollout guardrail mechanisms that stabilizes multi-agent RL training, supporting DualSQL to keep improving during training. We also introduce a new SQL correctness metric, robust execution match (REX), to more accurately judge SQL correctness and assign reward signals. Being trained on only 3755 examples, DualSQL-4B achieves an impressive 68.0% execution accuracy on the BIRD development set, matching previous 7B models. DualSQL-8B further improves to 71.1%, outperforming previous state-of-the-art single-model solutions with 32B parameters. These results demonstrate the strength of joint multi-agent reinforcement learning for building high performance Text-to-SQL pipelines.

Abstract: The emerging concept of data storytelling (DS) suggests that enhancing visualisations with annotations and narratives can make complex data more insightful than conventional visualisations. Previous works found that DS-enhanced visualisations are more effective than conventional visualisations for simple tasks like identifying key data points or the main message. However, no previous work has explored the extent to which DS enhancements influence task completion across different levels of cognitive complexity. We address this gap by presenting the results of a study where 128 participants completed tasks based on four visualisations (two line charts and two choropleth maps, either with or without DS elements) spanning a range of complexity based on Bloom's taxonomy, which has been applied in data visualisation to categorise tasks hierarchically from lower to higher-order thinking. Results suggest that while DS-enhanced visualisations effectively support lower-order tasks (finding data points and understanding insights), they don't necessarily aid the correct completion of higher-order tasks (application, analysis, evaluation and creation). However, DS enhancements improve how efficiently participants complete complex tasks.

Abstract: Comprehensive structured data on inter-firm relationships is often scarce or inaccessible because many relationships are privately negotiated, selectively disclosed, and fragmented across proprietary databases. This scarcity hinders the discovery of collaboration opportunities, particularly for startups and small and medium-sized enterprises. Firm profiles are readily available, but collaboration potential cannot be inferred from business similarity alone, since similar firms may be competitors, whereas dissimilar firms may offer complementary products, technologies, channels, capabilities, or capital. We present FirmCORe (Inter-Firm Collaboration Opportunity Reasoning), a human-annotated benchmark for pairwise reasoning over weakly structured firm profiles, comprising 2,805 labeled firm pairs. Given two firm profiles, a model must determine whether the available evidence supports a collaboration opportunity and, for positive pairs, jointly predict its strength, primary collaboration type, and role direction. FirmCORe also provides parallel Chinese- and English-language evaluation sets containing identical instances and gold labels, enabling controlled analysis of input-language sensitivity. Experiments with representative locally deployed and hosted large language models (LLMs) show that the strongest model achieves a macro-F1 score of 74.51 for opportunity detection but only 61.57% exact match across all four output fields. Language effects vary across models, and high cross-language agreement can mask errors shared across languages. These results indicate that current LLMs are substantially more reliable at detecting broad collaboration opportunities than at identifying their specific types and role directions.

Abstract: Real-world visualization requests are routinely ambiguous, incomplete, or factually incorrect, yet existing Text-to-Visualization (Text-to-Vis) systems assume well-specified inputs and produce charts in a single pass. When queries are imperfect, a system must \emph{interact} with the user to recover the true intent, but no benchmark or method supports this dynamic process. We introduce \textbf{VisInteract}, a new paradigm that reframes Text-to-Vis as interaction-driven intent recovery, and \textbf{VisInteract-Bench}, to our knowledge, that is the first benchmark for dynamic interactive Text-to-Vis, featuring controlled imperfection injection, a leakage-controlled User Agent for realistic multi-turn feedback, and dual-perspective (code and chart) automated evaluation. On the algorithmic side, we propose \textbf{Vis-MCTS}, a Monte Carlo Tree Search (MCTS) enhanced method, introducing improvements over classical MCTS, that \emph{Progressive Widening} to tame the unbounded tool-argument space in tree search, \emph{cross-rollout information sharing} so clarifications and critiques benefit the entire search tree, and \emph{Dimension-Aware Reward Decomposition} that routes scalar user feedback along data-fidelity, visual-design, and intent-alignment dimensions to resolve credit assignment across heterogeneous actions. Extensive Experiments across two LLM backbones show that Vis-MCTS consistently outperforms all Text-to-Vis baselines, improving end-to-end task success by $13.40\%$--$16.27\%$ over the strongest interactive baseline and by more than $5\times$ over non-interactive ones.

Abstract: Most time series forecasting benchmarks remain numerical-centric and provide limited support for evaluating contextual information that shapes real-world temporal dynamics. Existing multimodal benchmarks also suffer from limited data and context coverage, fragmented evaluation settings, and overreliance on aggregate evaluation. In this paper, we propose \textbf{MUSE-Bench}, a unified benchmark for multimodal time series forecasting with heterogeneous context. It comprises fourteen datasets across eight domains and six types of context: metadata, events, holidays, news, images, and numerical covariates. We evaluate diverse forecasting paradigms, including statistical, data-specific, foundation, multimodal, and general-purpose LLM forecasting methods under shared non-overlapping forecast windows, common target observations, and consistent point and probabilistic metrics. Extensive experiments yield three main findings. First, numerical time series foundation models dominate the overall ranking, while Aurora, the evaluated multimodal foundation model, trails the leading numerical TSFMs but outperforms all evaluated data-specific models. Second, ablations show that external context improves the four evaluated context-aware models, whereas incorrect or temporally misaligned context degrades performance. Third, general-purpose LLMs perform poorly as direct forecasters, and LLM-guided refinement does not yield consistent improvements. MUSE-Bench enables systematic evaluation of how forecasting models utilize context and provides a foundation for future multimodal forecasting research.

Abstract: Large language models are increasingly used as natural-language interfaces to structured data, yet they remain unreliable when answers require consistent evidence conditioning, dependency-aware reasoning, and uncertainty estimation. Bayesian networks provide an explicit probabilistic reasoning layer, but learning useful structures from data remains costly and fragile at scale. We introduce ABSOL, a hybrid LLM-guided Bayesian network structure-learning framework that uses LLMs as bounded semantic guides. Across five discrete BN benchmarks spanning 27 to 1041 nodes, ABSOL is the only evaluated method to produce a viable graph on every benchmark, and achieves the highest Edge F_1 on every benchmark larger than 27 nodes with GPT-5.4. The four LLM augmentations, which contribute complementary semantic evidence to the statistical backbone, improve Edge F_1 over the non-LLM aggregation backbone by +0.23 on average. Complementary post-hoc refinement experiments suggest that these gains depend in part on limiting the LLM's authority over the final structure. Together, these results show that language-derived semantic knowledge can substantially improve scalable probabilistic structure learning when used as bounded guidance within a statistically grounded reasoning pipeline. The code for ABSOL is available at github.com/megagonlabs/absol-bn.

Abstract: Vision--language models (VLMs) can answer chart questions accurately, but output accuracy does not show how they combine the evidence needed to recover an exact value. We study vertical-bar value reading with controlled counterfactual activation patching in Qwen2.5VL-7B-Instruct and InternVL3.5-8B. The study connects three analyses: (1) The single-factor results show that the changed bar-top region restores much more answer preference than the unchanged bar body, despite containing fewer visual tokens. Legend- and series-related states also lose local recoverability earlier than bar-geometry and axis-scale states. (2) In the handoff analysis, restoration shifts from visual legend regions in early layers to prompt-series positions in middle layers. Resetting the prompt-series state selectively reduces legend-source rescue, supporting its role as a partial mediator. (3) In the factorial analysis, both models can use geometry and scale states from separate donors to favor the combined target. InternVL performs similarly when the states come from separate donors or one image, while Qwen shows lower restoration for separate donors which suggests higher context sensitivity. Together, these results provide preliminary causal evidence for localizing the internal computations that support exact bar-value reading.

Abstract: Relational table learning has recently emerged as an important research direction for modeling multiple tables connected through primary key-foreign key (PK-FK) relationships. Despite recent advances, a principled modeling framework tailored to this task remains underexplored. In this paper, we propose Intra-Inter Relational Table Learning (InRTL), a unified framework that explicitly models dependencies both within and across relational tables. Specifically, InRTL formalizes two complementary interaction patterns: intra-table interactions, describing associations among rows within the same table, and inter-table interactions, describing dependencies between rows across PK-FK-linked tables. To model these dependencies, we develop a column-aware table encoder to generate initial row representations, followed by Transformer-based self-attention and cross-attention modules for intra-table and inter-table learning, respectively. To further improve scalability, InRTL incorporates linearized attention and heterogeneous graph neural networks to simplify the self-attention and cross-attention operations. Extensive experiments on ten datasets covering 24 real-world tasks demonstrate the effectiveness of our approach. Code is available at https://github.com/W1nterFloW/InRTL.

Abstract: Causal graphs represent structural relationships among variables, yet users must still interpret direction, mechanism, and adjustment conditions in relation to the task at hand. Prior work often compares explanation formats as fixed conditions and pays less attention to how users distribute reasoning across graphs, direct explanations, and stories. We developed CoNS-Explorer, which uses reviewed instructional DAGs/SCMs to maintain a shared causal-fact ledger and generate fact-matched direct explanations and contextualized stories. A controlled survey experiment ($N=240$) compared the two texts as complete presentation packages. In the primary GLMM, the Story condition had a positive but uncertain overall association with accuracy (OR $=1.55$, 95\% CI $[0.34,7.10]$, $p=.572$); a population-averaged GEE showed a significant positive effect (OR $=1.89$, 95\% CI $[1.02,3.48]$, $p=.042$). Task-type interactions localized the clearest advantage to total-effect adjustment. Story also significantly increased situational presence. In a separate system-task and interview study ($N=24$), participants freely used graphs, direct explanations, and stories across three causal models. They established structural anchors with graphs and numerical results, consulted text when direction was unclear, mechanisms were unfamiliar, or multiple paths competed, and checked their judgments against other representations or external evidence. Integrating the two studies, we develop a process framework of structural anchoring, uncertainty triggering, explanation routing, and cross-calibration, together with four testable design propositions for adaptive causal explanation.

Abstract: Recently, a wide range of recommendation algorithms inspired by deep learning techniques have emerged as the performance leaders on several standard recommendation benchmarks. While these algorithms were built on different DL techniques (e.g., dropouts, autoencoder), they have similar performance and even similar cost functions. This paper studies whether the models' comparable performance are sheer coincidence, or they can be unified under a single framework. We find that all linear performance leaders effectively add only a nuclear-norm based regularizer, or a Frobenius-norm based regularizer. The former ones possess a (surprising) rigid structure that limits the models' predictive power but their solutions are low rank and have closed form. The latter ones are more expressive and more efficient for recommendation but their solutions are either full-rank or require executing hard-to-tune numeric procedures such as ADMM. Along this line of finding, we further propose two low-rank, closed-form solutions, derived from carefully generalizing Frobenius-norm based regularizers. The new solutions get the best of both nuclear-norm and Frobenius-norm world.

Abstract: Multimodal forecasting models that combine time series with text annotations promise richer prediction through textual context, but how do we know whether a text annotation meaningfully contributes to the forecasters prediction? This is an information-theoretic question, but to evaluate whether information-theoretic metrics can reliably measure the predictive value an annotation provides, a ground truth benchmark is needed, and none currently exist. We create a synthetic time series signal with annotations in three categories: semantically correct, incorrect, and irrelevant. Because the data generation process is fully controlled, ground-truth information content is known exactly, enabling principled evaluation of six complementary mutual information estimators (KSG, MINE, InfoNCE, CCA, PID and V-information). We show that all six estimators identify correct annotations as most informative, and are able to audit the quality of mixed text corpora, choosing the annotations that result in the best downstream forecasting results without the need for model training. Our benchmark identifies limitations of each estimator, and these are validated on seven real-world datasets, which show how estimator performance differs on weak signals. Finally, we establish practical rules for implementing these metrics for annotation auditing and fusion selection.

Abstract: Sports data analysts translate domain questions into insights by combining computation with sport-specific domain expertise. Large language models ease programming, but prompt-to-report workflows may obscure decisions and evidence. We present AI Soccer Analyst, a mixed-initiative system with revisable stages: Data Understanding, Problem Definition, Structured Planning, Execution, Evidence-Grounded Reporting, and Interaction and Refinement. A formative study with five analysts first informed design goals for automation, verifiability, human control, and accessibility. Subsequently, a task-based evaluation with 16 participants combined system logs, retained artifacts, ratings, and open responses; 33 of 48 tasks met the operational completion criteria. Exploratory tests supported favorable participant perceptions of completed-task output quality, task achievement, reliability, and verifiability after Holm correction. Interaction records showed domain knowledge emerging through clarification, planning, and refinement. These findings position stage-aware human-AI collaboration as a practical approach for producing inspectable, revisable, and verifiable analyses while retaining domain-expert involvement in consequential decisions.