financial technology teams

Abstract: Financial AI workflows that reuse investor knowledge need persistent memory that integrates observations across sources and periods without losing identity or provenance. In a knowledge graph, recurring observations may use different surface forms, fragmenting relationship histories and preventing evidence from accumulating. We introduce Fusion and Identity Registry for Memory Evolution (FIRME), a registry-anchored memory graph that reconciles incoming observations to persistent canonical relationships and retains their source, time, and context. Within periods, rule-based fusion links investor-call discussions to portfolio cash-flow signals, directly or through a fixed product-topic ontology. Across periods, canonical identities and persistent aliases direct recurring observations to the same relationship history; deterministic updates summarize reinforcement, inactivity, and reactivation. We evaluate FIRME on proprietary investor-call and cash-flow records and on S&P 500 earnings-call transcripts. Compared with a historical registry that retains canonical identities and semantic fallback but omits alias memory, FIRME increases final-period Correct Match Rate by 7.8-12.1 percentage points across four dataset-backend settings under a fixed-judge and fallback-review protocol. A blinded human audit of 200 incoming observations per setting finds Correct Match Rate gains of 9.0-16.5 points and reattachment-recall gains of 22.5-29.0 points, with higher observed merge precision in all four samples. A separate audit finds valid evidence paths for 293 of 300 outputs from full within-period fusion in the investor-call setting. Extraction-faithfulness and round-trip diagnostics assess source grounding and preservation of extractor-derived graph content.

Abstract: Large language models (LLMs) can read startup pitch decks, but letting them emit investment scores directly invites score inflation, run-to-run variance and rationales that are hard to audit. We describe DealsFlow, a human-in-the-loop agentic harness deployed at a UK early-stage fund. The LLM reads the deck, cites evidence and rates each category; code combines the ratings, caps them and only ever lowers them. Three mechanisms implement this: a stage-aware corroboration ceiling (78, 70 or 60 out of 100) on factual categories without external evidence; a sceptic call that may lower but never raise a score; and a pre-fetch pattern that retrieves and indexes all evidence before a single generation pass. We evaluate on $N=243$ SEIS/EIS investments with recorded outcomes. Because recent investments have unresolved outcomes, we use the 142 that are at least three years old. There, the full pipeline's score has Spearman $ρ=0.45$ (95% CI 0.32 to 0.57) with the total-value multiple and AUC 0.71 for identifying write-offs, against $ρ=0.38$ and AUC 0.68 for an unconstrained LLM. The gain is small and comes mostly from the sceptic call; we did not test whether its lower-only rule matters. Investments that later exceeded $2\times$ had 64% of factual categories corroborated, against 38% for write-offs (omnibus Kruskal-Wallis test over five outcome groups, $p=0.031$), and our retrieval was not date-restricted, so these figures may overstate screening skill. In a study of 20 inbound applications, analyst time per application fell from 44.7 to 18.9 minutes including verification and correction, and 84% of 240 cited claims were fully supported by their sources, but 70% of reports needed at least one correction.

Abstract: Foundation models promise reusable capabilities and step-change performance gains across tasks. In finance, large-scale pretraining of domain-specialized foundation models can advance both goals. However, prevailing architectures and objectives do not by themselves address the combined demands of financial systems: partial observability, interacting entities, asynchronous events, changing regimes, action-dependent outcomes, and rare states with disproportionate consequences. Moreover, independently developed specialists may learn incompatible representations, while multi-domain monolithic alternatives couple data access, model updates, and governance. We therefore propose a structured-data-first research agenda centered on modular, domain-specialized financial foundation models connected by a representation fabric for reuse and composition across domains and tasks. These models should maintain persistent financial state across aggregation levels and time horizons, capture its dynamics, and simulate action-conditioned futures, while remaining calibrated across regimes and for tail outcomes. They must also learn efficiently under data and access constraints and provide faithful, traceable explanations. We identify research challenges, directions, and capability-oriented evaluation criteria.

Abstract: Similarity-gated coverage does not establish that retrieved evidence contains the facts needed to answer a question. We audit Mexican-Spanish financial-regulatory QA and find that 35 of 135 covered items lack some or all load-bearing facts. On the post-hoc full-evidence slice (n=98), eleven prompt-matched models score 95-98/98 and none differs significantly from the anchor; this does not establish equivalence. Removing evidence-defective items changes the nominal significance status of 14 of 55 pairwise comparisons. On 56 zero-evidence items, accuracy spans 33.9%-89.3%. Removing evidence from the audited items under an abstention-permitting prompt reduces accuracy by 63-81 percentage points in all ten tested legs, with no recovered items. Building on sufficient-context research, we contribute MexRegQA v1.0: 192 items with provenance and evidence-status labels, frozen retrieval evidence for 191 evaluated items, predictions, judge outputs and offline checks. The audit was outcome-aware, the later model/panel sweep reused the same questions, and all reported scores and labels rely on machine evaluation without independent human validation. We propose releasing evidence-status labels alongside grounded QA benchmarks so that model comparisons can be examined separately from evidence availability.

Abstract: Computational models developed in .NET often need to run locally within web applications. We present Backend--Frontend Converter, an architecture for generating TypeScript implementations of component-based models. The converter maps components, connections, aliases, and formula trees to model-specific TypeScript code. Reusable runtime libraries provide numerical integration, data access, and state handling. We evaluate stored generated implementations through four orbital scenarios and a recorded trading-strategy comparison. Orbital calculations execute in a browser and are paired with C\# results by crossing event and timestamp; trading outputs are aligned by date. Analytic scheduler tests and deliberately perturbed outputs assess the validation procedure. Each orbital scenario produces 91 paired events with identical timestamps. Position and velocity differences remain below $(10^{-6}\)~km$ and $(10^{-9}\)~km/s$. All 20 analytic scheduler checks pass, and the comparator detects each of three prescribed state and time perturbations. The trading comparison contains 501 aligned daily records with matching indicator values, positions, and order events. The evaluated implementations preserve the compared outputs across the C#/TypeScript boundary. Component-specific generation and reusable execution libraries provide a practical route from supported .NET computational models to TypeScript applications.

Abstract: Which inputs drive a language model's financial forecast? We construct synthetic earnings announcements that independently reverse 20-day momentum, non-informational commentary tone, and whether fixed actual EPS beats a manipulated consensus. Six instruction/chat checkpoint conversions from four families (0.49-7.61B base parameters) receive 2,016 prompts each under a direct-answer Q8_0 protocol. The design includes 24 numerical blocks, six commentary pairs, profits and losses, rising and falling annual EPS, and two surprise sizes. Both A/B answer assignments and U/D cover all 384 primary scenarios per conversion. We estimate matched changes in conditional answer-prefix scores, not calibrated market probabilities. Across these checkpoints, the primary EPS contrast ranges from -0.19 to 86.80 percentage points. The magnitude of the primary signed tone contrast exceeds that of EPS in 5 of six models, and momentum exceeds it in 5. Natural-word numerical diagnostic accuracy ranges from 51.0 to 95.8 percent. Answer-encoding, wording, context, and conversion controls qualify these results. The experiment measures observable input reliance and numerical recognition; it establishes neither an internal reasoning mechanism nor realized return predictability. Public benchmark prompts, recorded scores, and an interactive recorded-results explorer accompany the study.

Abstract: Learning dealer agents can settle on persistently wide quotes, raising what customers pay to trade. A venue can route more orders to tighter quotes, but a wide quote may reflect real risk, and once dealers adapt, an end-to-end comparison cannot show why a rule works: because it intervenes more, picks better moments, is announced in advance, or rewards the right quote. We propose SOFA (State-aligned Order-Flow Allocation), a public order-flow contract with three parts: a State Scorer ranks market states from lagged public data, a Commitment Scheduler announces a budgeted intervention strength before dealers quote, and a Quote-to-Flow Allocator shifts a bounded share of fixed customer demand toward tighter quotes. Our paired re-adaptation protocol gives competing rules the same intervention strengths, only re-timed, lets dealers re-adapt to each rule from a shared checkpoint, and breaks one link at a time. Across 20 independently trained dealer populations in an ABIDES market, concentrating the intervention in states that the score ranks as low-risk lowers low-risk execution cost relative to random timing in every population, by 0.040 tick on average, while a stale announcement or a broken quote-to-flow link raises this cost. In the primary setting the gain comes at the expense of high-risk trades, whose costs rise, so state alignment pays off only for a venue that weighs low-risk costs more than 1.38 times as heavily as high-risk costs. Our code is available at https://github.com/moderncavemann/state-aligned-order-flow-contracts.

Abstract: Evaluating agents by outcomes alone can obscure the capabilities that produce them. This problem is especially pronounced in evolving environments, where outcomes reflect a closed-loop interaction between agent behavior and changing external conditions. We introduce LiveMACEBench, a process-aware benchmark that uses live financial markets as a naturally evolving testbed for persistent LLM agents. Five frontier LLMs operate along continuous trajectories under matched Tool Use, Persistent Memory, Rule Following, and Multi-Agent Collaboration configurations. We evaluate them through both realized outcomes and mechanism-specific diagnostics derived from complete decision traces. Across 30 days of live evaluation, we find a pronounced outcome-capability gap: realized returns often diverge from capability-specific measurements, and similar outcomes can arise from markedly different patterns of mechanism use. Trace-level diagnostics further expose distinct bottlenecks across capabilities, demonstrating that mechanism access, effective mechanism use, and downstream performance are not interchangeable measures of agent capability. LiveMACEBench makes this distinction measurable, turning live markets from a performance leaderboard into a diagnostic environment for agent capability

Abstract: AI agents can take actions. At times, those actions can go beyond what is intended. Agent reliability can be defined as assurance that an agent will stay within intended bounds and operate within limits. Today, there is no shared framework or language for describing, validating, and benchmarking the reliability of agentic deployments in financial services. This makes it difficult for financial institutions, vendors, and regulators to assess and trust agents at scale, thus limiting the pace of development and adoption. A standardized, shared representation of agent reliability would fill the gap. This paper introduces the Agent Reliability Profile, a per-agent unit of assurance evidence for agent deployments in financial services. Each Profile records a bounded, falsifiable claim, this agentic system reliably functions within its operating boundary. We define "operating boundary" as an agent having; (1) a defined autonomy tier, (2) a defined operational design domain, (3) defined classes of action, and (4) a defined control envelope. Production assurance progresses through three levels while the Profile schema remains constant: a Profile Builder compiles a Level 1 Asserted Profile from institutional evidence, a Profile Validator tests the deployment in its own environment to produce a Level 2 Validated Profile, and operation of the same tests by a qualified independent assessor produces a Level 3 Verified Profile. Separately a Benchmarked Profile reports results comparable across institutions under reference conditions. We describe the architecture, the artifact, the assurance ladder, the comparability flag, associated tools, an evaluation methodology, applications for financial institutions and supervisors, limitations, and a staged implementation program.

Abstract: Financial question answering often requires precise numerical extraction, unit handling, and arithmetic over tables and text, but applying expensive verification uniformly wastes test-time compute. We propose BudgetVerify, a budget-tiered generator-verifier framework that routes each generated answer to one of three verification tiers: no verification, lightweight check-and-revise, or higher-cost solve-first-then-compare verification. The router is trained from offline correctness and token-cost outcomes and, at test time, selects a verification tier using information available before verification, including the question, context statistics, the generated answer, and associated generator metadata. The selected tier either returns the generated answer directly or invokes the corresponding verifier. Across six commercial and open-weight base models, BudgetVerify consistently produces more efficient accuracy-cost Pareto frontiers than fixed verification policies by selectively allocating stronger verification only when it is useful. Although absolute performance varies across models, these efficiency gains and the resulting qualitative frontier shape are consistent across generator models.

Abstract: As AI agents are becoming widely adopted in the financial services industry, careful measurement is essential to understand where they can be reliably deployed and where oversight and professional review remain necessary. Such measurement, however, is constrained by limited access to proprietary or privacy-sensitive data. Existing benchmarks therefore often rely on publicly available data, human- and/or LLM-authored tasks, or simplified settings. We introduce FinancialAuditBench, a benchmark for evaluating agents on financial statement audit tasks, along with a framework for systematically generating synthetic engagements. Our task generation framework leverages differentially private aggregate statistics from historical audits along with audit expertise contributed through over 1,100 hours of benchmark development and review. FinancialAuditBench consists of 90 tasks spanning workpaper completion and review across six synthetic audit engagements, each containing an average of 179 files. Evaluation on eleven frontier models shows that while agents complete substantial portions of staff-level audit tasks well, they sometimes perform inappropriate procedures or produce incorrect documentation. Beyond financial auditing, our framework offers an approach for systematically generating synthetic tasks for model evaluation and training in privacy-sensitive domains.

Abstract: While inference-time reasoning in large language models (LLMs) promises better decision making, its higher computational cost may not yield better economic outcomes. Yet reasoning controls are rarely evaluated as economic interventions, where changes in model outputs must translate into better portfolios after trading costs. We conduct a controlled study of representative LLMs from the DeepSeek, GPT, and Gemini families. We vary reasoning effort while holding information available at each formation date, prompts, output formats, and portfolio construction fixed. Our evaluation covers a full year of U.S. equities under three input conditions: numerical, identifiable news, and masked news. It includes more than 800,000 asset predictions and repeated model generations. Across all three model families, additional reasoning does not produce a reliable improvement in net portfolio returns. For DeepSeek, where we examine the full progression from no reasoning to maximum reasoning, performance is nonmonotonic. Repeated generations also produce unstable treatment effects and portfolio selections, even when overall scores remain similar. These findings show that additional reasoning can change financial decisions without reliably improving their economic value, motivating validation for each task before deployment.

Abstract: Large language models (LLMs) are increasingly used as user simulators, but their ability to reproduce evolving individual financial decisions remains unclear. We present a preliminary study in a controlled paper-trading environment with 120 volunteers. Participants used non-redeemable virtual funds under real-time market conditions; no real brokerage accounts, real-money positions, or real transaction records were accessed. Given only information available before a prediction cutoff, a simulator predicts the participant's next-trading-day action, traded security, and transaction quantity. We evaluate temporally aligned rolling predictions and compare settings with and without point-in-time market information. Market context improves action and ticker prediction in the controlled ablation, while transaction sizing remains difficult. We also observe systematic behavioral compression: models overproduce hold actions, underpredict sell decisions, and simplify multi-security transactions. These results provide an initial empirical characterization and motivate larger-scale evaluation of individual, temporal, and portfolio-level behavioral fidelity.

Abstract: Can financial vision-language models (VLMs) turn chart evidence into reliable action recommendations? Existing hallucination evaluations are mostly claim-centric; they assess whether generated statements are supported, but not whether evidence remains traceable through rationale, confidence, and final action. We introduce E2A-Bench, a 969-query benchmark for financial chart reasoning, constructed from 323 HS300 constituents under three input modalities with deterministic OHLCV-derived evidence anchors. E2A-Bench evaluates grounding, reasoning-action consistency, evidence-confidence calibration, and directional coverage through UCR, RCI, ECI, and NDR, where NDR measures coverage-aware evidence-to-action reliability rather than realized trading performance. Evaluating 20 VLMs reveals three failures hidden by scalar hallucination scores: the lowest-UCR model ranks near the bottom by NDR due to only 6.4% directional coverage; oracle-aided verification reduces unsupported claims but can collapse coverage; and financial fine-tuning amplifies the BUY:SELL ratio by factors of 4.21 to 4.68 across strict base-fine-tuned pairs. These results show that financial VLM evaluation should trace the full evidence-to-action chain rather than rely on a single hallucination score. Code and data: https://github.com/wanng-ide/E2A-Bench