Papers for
enterprise search teams
Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.
Research agents improve retrieval augmented generation with open-weight models
RMIT-ADM+S at TREC RAG 2026: Research Agents, Retriever Ablations, and Open-Weight Replication
Abstract: We describe the RMIT-ADM+S team's participation in the TREC 2026 Retrieval-Augmented Generation (RAG) track using the ClimbMix corpus. We submitted seven research-agent runs using proprietary OpenAI and open-weight models, exploring different retrieval strategies, writer models, and agent workflows. Pre-submission ablations identified writer selection and adjacent-chunk expansion as the main factors affecting answer quality. In the official NIST evaluation, six of seven runs exceeded the track median across all three rubric/nugget collections. Our best-performing run, brief-hybrid, achieved the highest all-item coverage among our submissions and tied the track maximum (0.892) for Batch-1 vital coverage. Human side-by-side preferences differed across evaluation batches: the open-weight owa-glm5 led Batch 1 despite lower automated coverage, while sol-research-first led Batch 2. These findings highlight differences between automated coverage measures and human preferences, as well as the potential of lower-cost open-weight models for research-agent systems.
OpticalRAG compresses long documents into few tokens with images
OpticalRAG: Pixel-Space Compression for Token-Efficient Retrieval-Augmented Generation
Abstract: Retrieval-augmented generation (RAG) is bottlenecked by the token budget of large language models: feeding long documents into the context window is expensive, while aggressive textual compression discards fine-grained information that is irreversibly lost in a one-dimensional token sequence. We argue that this bottleneck is not fundamental to information density but to the choice of compression \emph{modality}. Modern visual encoders can pack the contents of a rendered text page into roughly a hundred visual tokens with little semantic loss, opening a new compression-fidelity tradeoff that purely textual methods cannot reach. We present \textbf{OpticalRAG}, a framework that renders documents as page images, encodes them with a frozen vision encoder, and distills the retrieved visual tokens into as few as $16$ injected tokens before passing them to the LLM. Two ingredients make this work without expensive cross-modal training: (i) \emph{Encoder-Bridged Retrieval}, which projects text-query states into the visual feature space of the frozen encoder, through a projection shared with the compressor, to retrieve visual tokens from a text query, with no contrastive training; and (ii) \emph{Query-Driven Distillation}, a lightweight cross-attention compressor that condenses the retrieved visual tokens into a small set of query-conditioned prefix tokens. On LongBench-v2, BAMBOO, and LooGLE-v2, OpticalRAG achieves the best compression-aware accuracy (CAP) on all three benchmarks while injecting only $16$ tokens, and improves the closed-book Qwen2.5-7B-Instruct backbone by $5.17$ points on LongBench-v2.Code is available at https://github.com/brighterr/OpticalRAG.
Agentic graphrag uses symbolic knowledge to improve language model answers
Typed-Centrality Grounding for Agentic GraphRAG: A Symbolic Approach for Agentic Reasoning
Abstract: Knowledge Graphs (KGs) and Large Language Models (LLMs) represent two approaches for knowledge representation and reasoning over heterogeneous data. Recent research has explored their integration through Graph Retrieval-Augmented Generation (GraphRAG) systems, which use KGs to provide structured context to LLMs. However, existing GraphRAG approaches treat KGs as homogeneous graphs and rely on textual similarity between the input prompt and the context, rather than using it as a source of deterministic knowledge. This work proposes an agent-based GraphRAG system that introduces a symbolic layer to integrate deterministic reasoning alongside text similarities. This approach is based on the definition of typed centralities for KGs, where centrality measures are computed separately for each specific KG's class. This information is used to construct a symbolic representation that is provided to the LLM as a deterministic source. The proposed system was mathematically validated and evaluated on a real-world POLE (Person, Object, Location, Event) dataset, comparing reasoning and information retrieval with and without the symbolic layer. The results indicate that the our approach leads to responses that are more consistent with the context, improving the generated outputs.
Hvmap enables federated search across different vector databases
Federated Vector Retrieval across Heterogeneous VectorDBs
Abstract: Vector databases are now core infrastructure for AI retrieval systems, yet many real deployments must serve queries over multiple independently constructed vectorDBs built with different embedding models. This creates a systems problem of federated retrieval over heterogeneous vectorDBs: vectors and similarity scores are not directly comparable across embedding spaces, while fully resolving this incompatibility through corpus-wide re-embedding and re-indexing is often operationally prohibitive. Existing methods therefore face a difficult trade-off between retrieval quality, construction cost, and query throughput. We present HVMap, a lightweight compatibility layer for federated retrieval across heterogeneous vectorDBs. Instead of rebuilding databases into a unified space, HVMap learns bidirectional mappings between embedding spaces using a fuzzy contrastive loss, enabling calibrated cross-database scoring without corpus migration or index reconstruction. HVMap is system-agnostic and further scales to multi-vectorDB settings while preserving ranking fidelity through a hub-based architecture. We evaluate HVMap in open-domain, cross-domain, and scale-out settings, and also construct a new benchmark for heterogeneous cross-domain federation. Across these settings, HVMap consistently achieves a better quality--cost--throughput trade-off than baselines, achieving up to 3.59X higher nDCG@10, up to 2.01X higher query throughput, and construction time as low as 0.3% of baseline methods. These results show that HVMap makes heterogeneous vectorDB federation practical at scale.
SpectRAG builds better multi-hop retrieval contexts with weighted graphs
SpectRAG: Weighted Chunk Graphs for Token-Budgeted Context Selection in Multi-Hop Retrieval-Augmented Generation
Abstract: Retrieval-augmented generation (RAG) systems ground large language models (LLMs) by retrieving external evidence and conditioning generation on the retrieved context. Although dense retrieval is effective for local semantic matching, independently ranked retrieval can return redundant passages, miss cross-chunk dependencies, and provide incomplete evidence for multi-hop reasoning. We propose SpectRAG, a spectral graph-augmented retrieval framework that combines hybrid candidate seeding, weighted chunk graph construction, graph-based expansion, spectral relevance propagation, and token-budgeted context selection. Document chunks are represented by dense semantic embeddings and graph-spectral coordinates derived from a weighted chunk graph whose edges encode semantic similarity, document adjacency, section hierarchy, shared entities, citation links, and similarity between LLM-generated utility questions. At query time, SpectRAG builds a high-recall seed set using exact inner-product search and hybrid relevance signals, expands it over the chunk graph, re-scores candidates using graph proximity and spectral information, and assembles the final context under a fixed token budget. The goal is not merely to retrieve individually similar chunks, but to construct a context that is relevant, diverse, structurally connected, and sufficient for grounded reasoning. Experiments on MultiHopRAG, UltraDomain, and long-document question-answering settings show that SpectRAG improves broad evidence recovery and achieves competitive generation quality against dense, hybrid, HyDE, LightRAG, and NaiveRAG baselines. The results further indicate that graph-spectral structure is particularly useful for inference-oriented and cross-document retrieval, while highlighting trade-offs in early precision, computational cost, and domain-dependent performance.
Large language models evaluated on long web search tasks with error tracking
LongSearchEval: Evaluating Long-Horizon Web Search Capabilities of Large Language Models via a Trajectory-Aware Agent Framework with Failure-Node Localization
Abstract: Long-horizon web search requires LLM-based agents to integrate information across web pages through extended interactions under task-specific constraints. Evaluating this capability is important not only for measuring final answer quality, but also for assessing whether an agent acquires, verifies, and uses evidence reliably over extended interactions. Existing evaluations, however, mainly rely on simulated trajectories or on post-hoc trajectories reconstructed from final answers, rather than on retained real interaction traces, which limits the fidelity of behavioral assessment and weakens support for fine-grained error localization. To address this gap, we introduce LONGSEARCHEVAL, a trajectory-aware agent evaluation framework that combines a unified agent execution protocol with source constrained outcome verification and retrospective failure-node localization. Stage 1 verifies answer groups against agent-cited webpages without human-authored gold answers; Stage 2 audits normalized rounds and links flagged failure nodes to incorrect answer groups. We evaluate 16 models from eight families on 100 tasks, yielding 1,600 retained runs and 6,545 automatically flagged failure nodes. Trajectory collection and evaluation required 1,037 and 318 hours of cumulative runtime, respectively. Human validation yields 94.50% agreement on supplied answer-group labels and 98.11% feature-correspondence precision for audited round-group links. Together, outcome scores and linked trajectory evidence support controlled model comparison and retrospective inspection of answer-related content.
GuardRAG defends AI answers from poisoned retrieval documents
GuardRAG: A Post-Retrieval Defense against Poisoning Attacks in Retrieval-Augmented Generation
Abstract: Retrieval-Augmented Generation (RAG) enhances the factual grounding of Large Language Models (LLMs) by incorporating external evidence, but also exposes them to corpus poisoning attacks. In particular, coordinated attacks can introduce multiple mutually reinforcing poisoned documents into retrieved contexts, making reliable evidence filtering challenging. To address this problem, we propose GuardRAG, a training-free and plug-and-play post-retrieval defense that exploits the semantic structure of retrieved evidence to identify suspicious document groups. Specifically, GuardRAG first expands the retrieval range and removes near-duplicate candidates, then partitions the retained documents using Hierarchical Agglomerative Clustering (HAC) with a query-adaptive threshold. Finally, it scores and prunes suspicious clusters based on query relevance, cluster size, and semantic compactness. Experiments across three question-answering datasets, multiple poisoning attacks, and six LLMs demonstrate that GuardRAG substantially reduces attack success rates while maintaining answer utility under clean retrieval.
Hybrid retrieval fusion can lower quality on some search queries
The Fusion Tax: A Diagnostic Analysis of When Hybrid Retrieval Hurts
Abstract: Hybrid retrieval, which fuses a sparse lexical retriever with a dense neural one, is widely recommended in the software documentation surveyed in September 2026, usually with reciprocal rank fusion (RRF), on the strength of aggregate gains. We ask what fusion costs on individual queries, treating "do not fuse" as a first-class outcome, in the setting in which hybrid retrieval is deployed: a standard Anserini BM25, five dense encoders spanning 22M-596M parameters and three model generations, a learned-sparse (SPLADE) alternative, and a cross-encoder second stage, on seven BEIR datasets and three fusion functions. Even the best method, dense-weighted score interpolation, ranks relevant documents below the better of its two components on 13-48% of queries and below the deployable dense-only retriever on 8-21% (14-48% and 11-25% at a weight selected under leave-one-corpus-out validation), while beating dense-only in aggregate on every corpus with the primary encoder; the downside is significant under loss-averse risk-sensitive evaluation on six of the seven corpora. We call this loss the fusion tax. It is mostly a ranking effect that preserves recall in aggregate, it is most likely on the queries that only one retriever covers, and it persists across the encoder ladder and the SPLADE substitution. RRF carries the higher tax wherever the dense retriever is clearly stronger and only beats dense-only where the two components are balanced. Fusion failure is weakly predictable within a corpus but transfers unreliably across corpora, because the features that predict it change sign with the sparse-dense balance. A cross-encoder recovers part of the tax only where it is itself reliable. We distill these findings into guidance that keys the fusion decision to the measured sparse-dense balance of the target corpus.
Embedding free multi hop retrieval achieves strong results with bm25 and jev
SAG2: Embedding-Free Multi-Hop Retrieval with BM25 and JEV
Abstract: Strong multi-hop retrieval should be practical to deploy without expensive corpus preparation or complex database infrastructure. We present SAG2, an embedding-free retrieval architecture built around a single SQLite database, BM25, and contextual evidence decisions from JEV. SAG2 follows the query-time association principle of SAG (SQL-Retrieval Augmented Generation), while replacing its event-entity and dense indexes with a lexical index over original passages. Selected passages supply terms for further retrieval, and newly retrieved evidence guides subsequent decisions. This moves semantic evidence selection to query time, eliminating offline embedding computation, LLM-based event-entity extraction, and dedicated database servers. The resulting system combines lightweight preparation with strong retrieval accuracy: on 1,000-question subsets of MuSiQue, 2WikiMultiHopQA, and HotpotQA, SAG2 achieves the highest Recall@5 and Recall@10 among the compared methods, with Recall@10 of 86.62%, 97.43%, and 99.00%. It also reaches 81.10% document Recall@10 over the 511,962-document EnterpriseRAG-Bench corpus. Indexing all 11,656 MuSiQue passages takes 2.36 seconds, produces a 25.87 MiB database, and requires no model calls. SAG2 demonstrates that accurate multi-hop evidence retrieval can be supported by compact, rapidly prepared infrastructure, making it a practical foundation for knowledge retrieval applications.
Causally guided retrieval agent improves question answering over knowledge graphs
CARA: Causally Guided Retrieval Agent for Question Answering
Abstract: Retrieval-augmented generation over text-rich knowledge graphs requires identifying evidence that contributes to answering a question, rather than merely matching its textual content. Existing agentic retrievers adaptively balance global search and multi-hop exploration but primarily rely on textual similarity to guide retrieval. We propose CARA, a training-free, CAusally guided Retrieval Agent that explicitly evaluates the causal relevance of retrieved evidence through two complementary criteria: consequentiality, measuring whether adding evidence improves answerability, and essentiality, assessing whether removing evidence weakens answerability. CARA integrates these assessments with path consistency to guide graph exploration and employs reciprocal rank fusion to aggregate evidence from multiple agents. We evaluate CARA on three STaRK datasets and augment STaRK with ground-truth answers to enable downstream question answering evaluation. Experimental results demonstrate that CARA consistently outperforms existing retrievers. CARA also improves answer quality and faithfulness while examining fewer graph nodes and requiring fewer retrieval operations. These findings demonstrate that causal relevance assessment enables more focused and effective agentic graph retrieval, improving both retrieval performance and downstream question answering.
Efficient document search improves speed and accuracy with cascaded retrieval
Cascaded Retrieval with Cross-Modal Query Refinement for Efficient Visual Document Search
Abstract: Retrieving information from visually rich documents requires matching queries against pages that contain complex evidence in tables, figures, and layout-dependent structures. Current vision-language retrievers address this but incur query-time costs that grow with corpus size and are impractical to scale. We propose SCOUT, a cascaded two-track retrieval framework that separates retrieval performance from exhaustive search. The visual track first uses a lightweight parent retriever to filter the corpus to a compact candidate pool, then applies a stronger multi-vector reranker only to those candidates. In parallel, a semantic track retrieves over hierarchical page and document summaries generated offline to provide a signal complementary to visual matching. The outputs are fused through cross-modal query refinement, which uses semantic scores to adjust the visual query representation before final ranking. We evaluate SCOUT on 4 major benchmarks against 6 baselines and observe a significant query-time latency improvement up to 80.7x (28.8x on average) relative to the best baseline, while exceeding state-of-the-art retrieval performance by up to 7.8% NDCG across all benchmarks.
Search agents improve reasoning by choosing evidence selectively
SEEDS: Preview-Guided Evidence Admission for Search Agents
Abstract: Search agents extend large reasoning models with multi-round access to external knowledge, yet most existing systems largely conflate retrieving evidence with consuming it. Retrieved documents are commonly incorporated according to fixed or rank-based policies, despite the fact that evidence utility is conditioned on the agent's current reasoning state. Consequently, a lower-ranked candidate may be critical for the current step, while a higher-ranked candidate may provide redundant, irrelevant, or misleading information. We formulate this overlooked problem as evidence admission, which asks, at each search step, which retrieved candidates should be allowed to enter the agent's evolving reasoning context. To enable such selective control, we introduce SEEDS (Selective Evidence Entry During Search), a preview-guided evidence admission framework for search agents. SEEDS first exposes lightweight previews of retrieved candidates and then lets the agent jointly determine which candidates and how many should be fully inspected, conditioned on its current reasoning state. Unlike fixed or adaptive prefix policies, SEEDS can select arbitrary subsets with flexible cardinality, and it can be instantiated directly with an existing reasoning agent or further optimized through learning. Across nine knowledge-intensive QA benchmarks under both local corpus and live web search, SEEDS consistently improves search effectiveness while substantially reducing full-evidence consumption. Experimental analyses show that SEEDS more effectively selects useful candidates beyond the corresponding retrieval prefix. These results establish evidence admission as a complementary dimension of agentic search, separating what information is retrieved from what information is ultimately allowed to shape reasoning.
Native unit retrieval improves question answering over structured documents
NativeScope: Relation-Localized Retrieval over Native Topology with a Correct Anchor
Abstract: Dense retrieval usually ranks text chunks by their semantic similarity to a question. This ignores structure that many data systems already store, including section membership, session boundaries, and native order. We propose NativeScope, a scope-then-rank method for queries with a known anchor and relation. It represents a query as q -> (A, r, B). The anchor A and relation r select native units through belonging, before, or after operators, and the target term B ranks only chunks that overlap the selected scope. An internal variant, NS-FullQ, ranks the same candidates with the full question. We evaluate both methods on 200 controlled document and memory records derived from QASPER and LongMemEval under a 1,024-token budget. NativeScope attains native-unit recall of 89.28 percent for documents and 72.50 percent for memories, improving over instance-wide Dense RAG by 42.75 and 22.00 percentage points. NS-FullQ reaches 87.78 percent and 68.50 percent; its differences from NativeScope are inconclusive, locating the primary gain in relational scoping rather than the shorter ranking query. With automatic Top-1 anchors, memory recall falls to 35.50 percent. NativeScope is therefore effective when anchor coordinates and native relations are reliable, but hard scoping inherits errors from the localization interface.
Visual document retrieval improves accuracy and reduces storage needs
EVIE: Evidence-Vector-Informed Embeddings for Visual Document Retrieval
Abstract: Accurate and scalable visual document retrieval (VDR) requires both fine-grained page understanding and efficient indexing, yet existing approaches struggle to achieve both. OCR-based text retrieval adds preprocessing latency and can lose visual and structural cues needed to understand complex pages. Single-vector vision-language models bypass OCR, but compressing an entire page into one vector limits the granularity of query--document matching. Multi-vector retrievers with MaxSim provide finer interactions, yet demand large indexes and still leave room for accuracy improvements. We argue that overcoming these limitations requires preserving query-relevant page evidence throughout representation learning and index construction. To this end, we introduce \textbf{\textit{EVIE}} (Evidence-Vector-Informed Embeddings), a family of native visual document retrievers integrating three key innovations: (1) Evidence-judged data governance, which uses a multimodal judge to identify answer-bearing positives and filter unreliable negatives. (2) Bidirectional teacher--student learning with symmetric listwise distillation and prefix-based Matryoshka representation learning (Prefix-MRL), enabling one student checkpoint to serve six nested embedding dimensions without re-encoding. (3) Hierarchical agglomerative index compression (HAC), which clusters page tokens with spatial regularization and stores semantic centroids for single-stage MaxSim retrieval. Extensive experiments across 138 tasks from ViDoRe V1, V2, V3, and JinaVDR validate EVIE. EVIE-8B achieves 66.75 nDCG@10 on V3, exceeding the best external baseline by 1.43 points, with a four-suite average of 79.51. EVIE-4.5B with HAC retains 59.58 nDCG@10 at only 3.81 GiB per million pages, reducing vector payload by $128\times$. Together, these results improve the accuracy--storage trade-off for visual document retrieval.
IndexAct improves agent search with smarter candidate refinement
From Delivery to Stateful Exploration: Rethinking the Index for Agentic Search
Abstract: Recent advances in agentic search have given large language model (LLM) agents finer control over corpus exploration. However, search interfaces often return matching passages even when feedback about the candidate set would suffice for the next decision, coupling candidate refinement with source-text exposure. We propose IndexAct, an interface for Index-Native Corpus Interaction that separates candidate-set refinement from text inspection. Agents construct and manipulate persistent candidate sets through lexical conditions and set operations over an inverted index, receiving reusable state references and statistics such as candidate counts rather than matching passages. This feedback guides further refinement, while separately requested passages provide new clues or evidence that can inform subsequent operations on retained candidate sets. Experiments on five benchmarks spanning agentic search and multi-hop question answering show that IndexAct outperforms the evaluated baselines on each benchmark. On BrowseComp-Plus, it also achieves higher evidence coverage with a smaller average live context than terminal-based corpus interfaces, and maintains answer accuracy as the corpus expands. Further analyses suggest that informative refinement feedback and state reuse support continued evidence discovery, while shorter contexts or fewer search steps alone do not ensure better performance.
Agentic retrieval improves complex search but needs more time
Beyond Semantic Similarity: Performance and Costs of Agentic Retrieval for Complex Tasks
Abstract: Modern information systems, including many agentic workflows, use dense retrieval to explore large amounts of unstructured data. However, dense retrieval relies on surface-level semantic similarity, which is insufficient for increasingly complex search applications. Here, we investigate agentic retrieval that combines the reasoning capabilities of Large Language Models (LLMs) with the efficient corpus exploration of retrievers in a ReAct agentic loop to solve complex retrieval tasks. In our experiments, we show that agentic retrieval is more effective than standard retrieval, improving nDCG@10 by 8.7 points using the same embedding model. Moreover, while specialized retrieval methods struggle on out-of-domain tasks, agentic retrieval is highly generalizable: the same pipeline achieves competitive results on both the ViDoRe v3 and BRIGHT leaderboards. However, this improvement comes at a cost. On average, agentic retrieval takes 107.4 seconds, compared to 0.67 seconds for standard retrieval, and consumes 764.1K input and 5.8K output tokens per query. In short, our study demonstrates the effectiveness of agentic retrieval in modern data systems and motivates future work on more cost-efficient retrieval agents for large-scale deployment.
Matrag improves multi-step question answering efficiency with hierarchical retrieval
A Matryoshka Hierarchical RAG for Efficient Multi-Hop Question Answering
Abstract: Retrieval-Augmented Generation (RAG) systems for multi-hop Question Answering (QA) must balance retrieval quality with computational cost. This cost is incurred during indexing time, through the use of expensive Knowledge Graphs (KGs) or Large Language Models (LLMs) to generate summaries, or during querying, through iterative LLM-driven retrieval. To reduce it while maintaining retrieval quality, we present MatRAG, a hierarchical framework that combines RAG systems with Matryoshka Representation Learning (MRL). MatRAG addresses both kinds of cost by aligning the semantic hierarchy of a clustering structure with the nested structure of MRL. Specifically, it organizes the corpus of documents into a Directed Acyclic Graph (DAG) of clusters with progressively coarser granularity. Each level is indexed by a lower Matryoshka dimension. MatRAG pairs an iterative, top-down traversal of the DAG with an entity-driven mechanism that controls the hop budget and re-ranks candidates. We evaluated MatRAG on three standard multi-hop QA benchmarks against seven representative baselines. MatRAG outperforms its strongest competitors in terms of retrieval quality; furthermore, it reduces indexing costs by avoiding KG construction and LLM-based summarization, and lowers query-time costs through dimension-aware similarity.
Canopy compresses multimodal evidence adaptively for better question answering
CANOPY: Adaptive-Granularity Evidence Compression for Multimodal RAG
Abstract: Multimodal RAG retrieves text, tables, images, and videos, but choosing a retrieval granularity does not determine how much context to retain within each item. Coarse units include irrelevant content, while uniformly fine selection can remove context needed to interpret the evidence. Existing compressors address this trade-off with modality-specific mechanisms, leaving open a shared procedure for adapting the retained extent region by region across heterogeneous items. We introduce CANOPY (Canonical Projection over Hierarchy), a framework for adaptive-granularity post-retrieval evidence compression. CANOPY represents retrieved items as hierarchies and uses a node encoder fine-tuned on gold evidence to score regions against the query. Parent-relative refinement compares these scores to select multiple regions at different granularities without LLM calls for node-level pruning. Because compression cannot recover evidence that was never retrieved, a critic requests targeted follow-up retrieval when it judges the accumulated evidence insufficient; newly retrieved items are compressed before being added. Across five QA benchmarks over a 33M-item heterogeneous corpus, CANOPY achieves higher average answer accuracy than the evaluated retrieval baselines. Ablations indicate that additional retrieval drives the main accuracy gains on multi-hop QA. In the unrouted Qwen3-VL-8B-Instruct setting, compression reduces reader-input evidence tokens by 14.2-27.7% relative to the same iterative pipeline without compression, with comparable answer accuracy.
Llm agents learn better search skills from fictional rule based worlds
PhantomEnvironments: Training LLM Agents in Fictional Worlds
Abstract: Training LLM agents with reinforcement learning (RL) is bottlenecked by environments, which must provide verifiable rewards, support long-horizon interaction, and scale cheaply. Existing approaches rely on costly human-curated data or on LLM-generated environments that risk hallucinations and benchmark contamination. We show that LLMs can instead be trained into capable search agents using synthetic environments generated entirely by rules, whose generation requires no LLM and has zero marginal cost. We build PhantomEnvironments, multi-turn RL environments from fictional worlds, where agents must search a corpus of templated articles to answer multi-hop questions. Despite sharing no facts with the real world, these strikingly simple environments yield agents that transfer to real-world multi-hop search benchmarks, often outperforming real-world training data on newer benchmarks. Trained agents generalize to unseen fictional universes, and Qwen models learn to scale their search budget roughly linearly with question difficulty, suggesting emergent search scaling from environment interaction alone. Ablating environment complexity reveals that hop count drives transfer more than constraints or comparisons: even the simplest rule-generated environments are a surprisingly effective, free resource for training generalizable LLM agents.
Context aware search shows improved accuracy over keyword methods
Towards Semi-Automatically Comparing Keyword-Based and Semantic Search Accuracy
Abstract: The increasing importance of Information Retrieval (IR) in managing large datasets has highlighted significant limitations in traditional keyword-based search systems. Context-aware chat-based search methods, such as Retrieval Augmented Generation (RAG), have recently emerged, but their evaluation compared to keyword-based systems often relies on subjective user feedback. A rigorous, quantitative comparison between these paradigms remains lacking. This work introduces a novel, preliminary framework to quantitatively assess IR accuracy of search systems that produce different output formats, such as lists and messages. It focuses on two key aspects: the ranking accuracy for keyword-based systems and the completeness of retrieved information for semantic chat-based systems. Our approach enables semi-automatic comparisons of semantic and keyword-based methods using interchangeable equivalence classes tailored to domain-specific contexts (e.g., companies or problems). We validate the framework through an industrial case study, demonstrating statistically significant improvements in context-aware search over keyword-based methods, supported by analyses including the Mann-Whitney U-Test. With its adaptable design, the proposed framework provides a strong foundation for objectively assessing keyword-based and semantic chat-based search methods.
Corpus map improves search by linking related entities across documents
Follow the Entities: A Corpus Map for Agentic Search
Abstract: Answering questions and completing tasks over large document collections often requires connecting evidence spread across multiple documents, such as a project's approval recorded in one, its requirements in another, and its latest status in a third. Recent LLM agents approach this by iteratively searching the full corpus rather than reading only a fixed set of top-ranked documents. However, when the corpus is exposed only as a flat collection of files, a relevant document gives no indication of how it relates to others, so the agent must rediscover these relationships for every query, often missing complementary evidence while simultaneously consuming substantial additional tokens. To address this, we introduce CorpusMap, a navigation layer that organizes the corpus around its recurring entities, which are identifiable from the documents themselves and can link a single document to many others across sources. Specifically, CorpusMap represents each recurring entity as an Entity Page that aggregates information about it and links to every document that refers to it, forming a graph between entities and documents that the agent can traverse to gather otherwise disconnected evidence. Moreover, since CorpusMap is constructed offline by resolving mentions of the same entity across documents, its links are shared across queries rather than rediscovered repeatedly at inference time. Using 7 different models with 3 benchmark datasets, we show that CorpusMap improves both evidence discovery and answer quality over raw-corpus agentic search while using fewer tokens on average, and further outperforms 4 alternative navigation layers, suggesting that entities serve as effective anchors for navigating large document collections.
Multi-vector visual document search sped up with smaller query models
ColNanoVDR: Document-Free Query Distillation for Multi-Vector Visual Document Retrieval via Optimal Transport
Abstract: Multi-vector retrievers built on vision-language models lead visual document retrieval (VDR), but they run a multi-billion-parameter query encoder on every search. Distilling this encoder into a small student that queries the teacher's existing index would remove the bottleneck. The standard recipe, however, matches the teacher's MaxSim scores and so requires encoding and caching every training page, which can reach terabytes of page tokens. NanoVDR avoids pages entirely by training on the teacher's query embeddings alone, but only for single-vector retrievers. We present ColNanoVDR, to our knowledge the first framework to bring this document-free distillation to multi-vector VDR. Its objective, OTW (Optimal Transport with Learned Weights), aligns the student's query tokens with the teacher's by entropic optimal transport, with a learned weight for each student token, and needs no correspondence between the two tokenizations. We prove that the resulting alignment cost bounds the MaxSim score difference on every page. Distilled from five state-of-the-art teachers, the 149M text-only students retain about 95% of their teachers' NDCG@5 on ViDoRe v1-v3 while encoding queries up to 26x faster. Under identical training, OTW matches score distillation while encoding no page and reading 12.6x less cached teacher data.
Multimodal embeddings read evidence boundaries to improve retrieval accuracy
Learning Multimodal Embeddings with Evidence-Aligned Readout
Abstract: Multimodal large language models can expose task-relevant evidence through generation, but producing useful evidence does not by itself determine how it enters a retrieval embedding. We study whether the semantic organization of that evidence can also specify where representations are read. To address this question, we introduce EviAlign, which couples Semantic Evidence Generation with Boundary Readout in a shared multimodal large language model. It organizes evidence into five semantic units, reads the contextualized state at each unit boundary, and aggregates these states into a single normalized embedding. Generation and contrastive retrieval objectives jointly train this shared structure. With the same trailing readout, semantic evidence and free-form CoT yield nearly identical retrieval performance, suggesting that evidence organization alone does not explain the full gain. A controlled $2\times3$ study compares consistent and permuted evidence organization across three readout strategies, using training targets with matched evidence spans. With five readout states and the same mean pooling, the advantage of consistent semantic organization grows from 0.65 points at length-based training positions to 2.39 at evidence boundaries, yielding a 1.74-point co-design interaction. Across 12 MMEB retrieval tasks, EviAlign achieves 76.9 average Recall@1 with 500K training pairs while retaining single-vector indexing and scoring.
HyperReCo improves evidence retrieval for multi-hop question answering
HyperReCo: Retrieving and Connecting Evidence with Hypergraph Neural Networks for LLM Multi-hop Reasoning
Abstract: Large language models (LLMs) have shown strong capabilities, with retrieval-augmented generation (RAG) supporting complex multi-hop reasoning by retrieving evidence distributed across documents. Graph-based approaches exploit connections among evidence, and hypergraph-based retrieval further preserves higher-order entity associations within documents and connects documents through shared entities. However, existing hypergraph retrievers often rely on predefined structural expansion or diffusion, which may miss query-dependent interactions needed to identify relevant evidence. They also leave connections among retrieved evidence implicit, requiring LLMs to reconstruct these connections before reasoning. Therefore, we propose HyperReCo, a framework for retrieving and connecting evidence with a hypergraph neural network (HyperGNN). We represent each document as a hyperedge over its extracted entities, with shared entities connecting the hyperedges. Through hypergraph message passing with joint supervision over documents and entities, the HyperGNN learns query-dependent interactions to retrieve complementary evidence. We further introduce Gradient-Guided Hyper-Path Decoding (GGHD), which uses gradient attribution to interpret the learned interactions and translate them into explicit hyper-paths that help LLMs combine complementary facts for multi-hop reasoning. Experiments on six benchmarks show that HyperReCo achieves the best retrieval performance among the compared methods on all three multi-hop QA datasets, together with strong downstream QA performance. Case studies and further analyses demonstrate the utility of decoded hyper-paths for connecting retrieved evidence.
Visual document retrieval improves by adapting queries with residual feedback
Test-Time Adaptation with Query-Dependent Residuals for Visual Document Retrieval
Abstract: Visual document retrieval (VDR) systems depend on page embeddings computed before deployment, which makes adaptation difficult when encoder parameters or corpus re-encoding are unavailable. Rerankers provide useful relevance signals, but conventional reranking applies them only to selected queries and candidate pages. We introduce Q-REACT, a query-side test-time adaptation method that converts limited reranker feedback into reusable retrieval improvements. Q-REACT learns a shared low-rank transformation that produces query-dependent residuals, combines adapted query scores with document-level context, and distills reranker preferences with a student distribution normalized over the complete task-specific page index. This design lets unscored pages compete through cached embeddings while keeping the encoders and page index fixed. Across eight ViDoRe V3 tasks and five open-weight and proprietary backbones, Q-REACT improves average retrieval over evaluated baselines at sparse and full-coverage budgets, transfers to held-out queries and tasks, and adds little inference overhead. The results show that finite reranker feedback can be amortized across a query collection without retraining or rebuilding the retriever.
Machine interpretable documents cut search and reading costs drastically
Machine-Interpretable Information: Compiling Documents into Searchable and Readable Protocol States
Abstract: Long-context language models interface with external knowledge through raw natural language. In retrieval-augmented systems, this creates a persistent index-payload schism: dense vectors enable searchable routing, but models must re-ingest lengthy text payloads for reasoning at O(N^2) attention cost. Existing compression methods further produce private states tied to specific architectures. We introduce Machine-Interpretable Information (MII), the first agent-to-agent (A2A) document-to-state protocol. A dual-timescale state-space Writer compiles documents into a canonical, fixed-bandwidth state (56 tokens), and a lightweight Translator maps it into any frozen Reader's embedding space, reducing query-time cost to O(K). The resulting .mii artifact unifies Retrieval (searchable geometry), Reasoning (global memory), and Reconstruction (grounded details) in a single transferable medium. We demonstrate strong cross-model interoperability across heterogeneous LLMs (e.g., Llama, Qwen, Mistral) -- despite the Writer using a legacy GPT-2 vocabulary, forcing genuine semantic translation rather than token-level memorization. Mechanistic probes reveal modular latent structure: entity representations can be causally traced and zero-shot transplanted between unrelated document states while remaining decodable. To address lexical reconstruction under fixed bandwidth, we propose Residual-MII, a cache hierarchy combining compiled global memory with sparse local evidence. On HotpotQA (7,405 queries), Residual-MII exceeds full-context Exact Match at approximately 7% of the attention FLOPs, suggesting a paradigm shift toward compiled, transferable neural document formats.
Hybrid document search method improves ranking on scientific fact dataset
Parameterized Dense-Sparse Fusion for Hybrid Retrieval: Tuning a Rank-Score Mix on BEIR SciFact with Qdrant
Abstract: We study a parameterized hybrid ranker that fuses a dense embedding list and a sparse lexical list. The method has a small, explicit parameter vector: a dense prior $α\in [0,1]$, a score-versus-rank mix $λ\in [0,1]$, an RRF smoothing parameter $κ> 0$, optional list-geometry coefficients that move $α$ per query, and a router margin $τ$ that can turn sparse search off. We grid-search those ranges on SciFact train (809 queries) and freeze the chosen values on SciFact test (300). The tuned rank-score mix ($α= 0.8$, $λ= 0.75$, $κ= 20$) reaches 0.753 nDCG@10 and 0.889 recall@10, outperforming dense BGE (0.742 / 0.871) and equal-weight RRF (0.707 nDCG@10) on that test split. A list-conditioned $α$ adds +0.0006 nDCG; a sparse-off router is rejected by the same train split (any $τ$ that skipped approximately 50% of queries lost nDCG). These coefficients are dataset-specific. Equal RRF with the same models does not beat dense on a nine-zip BEIR macro-average (0.479 vs. 0.519 nDCG@10). Repeating the same train-then-freeze sweep independently on all 20 indexed units beats equal RRF on 20/20 and dense on 16/20 (unit-mean nDCG@10 0.467 vs. 0.462 dense vs. 0.420 RRF). Other corpora should reuse the ranges, not a copy of the SciFact point.
Graph structure cuts cost and improves answers in document-based question systems
When Is Graph Structure Worth Its Cost? The Case for Structure Pricing in Retrieval-Augmented Generation
Abstract: Graph-based retrieval-augmented generation (RAG) can help answer questions that require information from many documents. However, building a graph often requires many language-model calls during ingestion. It is therefore important to ask whether its quality gains justify the additional cost. We present EffiRAG, a graph-based RAG system designed to reduce this cost. It uses the graph to locate relevant passages and generates answers from the original text. This design preserves source information while keeping graph construction and query processing lightweight. We evaluate EffiRAG on UltraDomain, which contains 120 open-ended questions from four domains. Compared with LightRAG-hybrid, EffiRAG produces the preferred answer on 93 questions. LightRAG is preferred on 7, and the remaining 20 are splits. EffiRAG also reduces total system cost by 57 percent, from USD 0.952 to USD 0.408. The cost includes language-model calls during ingestion and querying. The advantage remains as the corpus grows. At 10 and 20 documents per domain, EffiRAG uses a lightweight, non-LLM filter to skip low-salience chunks. It remains preferred over LightRAG-hybrid. It costs 4.2 times and 4.5 times less, respectively. The comparisons identify different quality-cost trade-offs. Graph-based RAG systems should therefore be evaluated by both answer quality and cost. The results favor graph structure that locates and preserves source evidence.
Query adaptive indexing improves retrieval in expert archives
ORDER: Task-Conditioned Routing for Retrieval-Augmented Generation
Abstract: Retrieval-Augmented Generation (RAG) pipelines typically rely on a fixed indexing and retrieval configuration determined at preprocessing time. This one-size-fits-all design is ill-suited to domain-expert settings, where heterogeneous queries require different chunking granularities, metadata constraints, and source-selection strategies. As a result, configurations that are effective for one family of queries often perform poorly for others. In this paper, we introduce ORDER (Optimal Routing for Dynamic Evidence Retrieval), a query-conditioned RAG framework that jointly adapts indexing and retrieval to the incoming query. Our approach first discovers semantic clusters over a given set of questions associated to a corpus and learns, for each cluster, a chunking strategy together with a suited metadata filtering and reranking configuration. At inference time, queries are routed to the appropriate pre-built index through nearest-centroid assignment. To further improve retrieval, we propose a supervised query router (QRe) that predicts which collections are most likely to contain relevant evidence, coupled with a Uniform Multi-source Sampler (UMS) that allocates the retrieval budget evenly across the selected sources. We evaluate our framework on large-scale, heterogeneous historical archives and show that conditioning both indexing and retrieval on the query consistently outperforms both naive baselines and strong state-of-the-art RAG systems in complex expert-domain environments.
Taxonomy creation improved by preserving structure in concept grouping
SPARROW: Scalable Taxonomy Induction via Structure-Preserving Partitioning and Constraint-Guided Merging
Abstract: Taxonomy induction aims to organize concept sets into coherent hierarchical structures. Recent LLM-based methods can induce taxonomies directly from flat term lists, avoiding the need for corpora, but degrade sharply as concept sets scale up. We argue that this degradation stems not only from context length limitations, but also from structural failures in hierarchical reasoning. To address this, we adopt a divide-and-merge paradigm that partitions concepts into smaller subsets, induces local taxonomies, and merges them into a global hierarchy. However, we identify two structural failure modes inherent to this paradigm: Structural Fragmentation, where partitioning weakens local hierarchical signals, and Parent Displacement, where locally plausible relations are misplaced in the global hierarchy. To address both, we propose SPARROW, a scalable taxonomy induction framework that combines structure-preserving spectral partitioning to retain hierarchical connectivity within each block, and constraint-guided incremental fusion that treats block-level relations as structural constraints rather than ground truth for global placement. Experiments on large-scale benchmarks show that SPARROW consistently achieves the strongest global structural quality across backbones. The code is available at https://github.com/rebeccazyr/SPARROW.