Finance

Follow this topic Ask about this topic

Momentum

9 papers in the last four weeks, level with the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 239

Aug 4, 2026cs.AI

FinPerMA: A Theory-Informed, Event-Grounded Personalized-Memory Benchmark for LLM Agents

Large language model (LLM) agents are increasingly used as personalized assistants in high-stakes domains such as financial advising, yet it remains unclear whether they can maintain and update an individualized user model over long horizons. Existing personalized-memory benchmarks primarily test factual retention or rely on weakly constrained model-generated trajectories, leaving event-driven preference adaptation underexplored. We introduce FinPerMA, an event-grounded benchmark that evaluates personalized memory against frozen longitudinal investor trajectories. Its generation pipeline combines deterministic, theory-informed impact rules, controlled LLM narration, and automated quality screening; a Post-Shock checkpoint isolates whether an agent has integrated a material event into its persistent user model. On 2,994 questions from 276 personas, seven frontier LLMs and up to seven memory configurations remain far from saturated: no full-context configuration exceeds approximately 0.47 overall accuracy or approximately 39% on multiple-choice questions. Attribution analysis shows that summary-based memory often preserves factual details while losing the preference signals needed for personalization; simple retrieval can therefore outperform purpose-built memory systems, with the gap widening after shocks.

Ben Wang, Kang Zhou, Lifan Guo +2

Qwen DianJin Team, Alibaba Cloud Computing

Financial Services LLM Agent Memory Memory Agent Benchmarks Finance

Aug 4, 2026cs.AI

FinProBench: Evaluating Financial AI Agents with Role-Grounded Rubrics Derived from Professional Deliverables

Evaluating financial AI agents requires criteria aligned with real professional work. Existing rubric methods typically derive criteria from task prompts or model outputs, overlooking tacit standards visible only in practitioner deliverables. We introduce FinProBench, a benchmark for professional financial tasks, and Role-Grounded Rubric Construction (RGRC), a reusable pipeline that derives rubrics from deliverables produced by practitioners in the same role. RGRC comprises four stages: Deliverable Collection, Competency Extraction, Rubric Synthesis, and Validation. Its rubrics capture tacit standards, distinguish quality levels, and transfer across tasks within a role. Before analysis, we classified 57 occupations by deliverable genre into 30 prior-rich conventional roles and 27 prior-sparse role-specialized roles. Across all roles, Prompt-only nearly matches RGRC for conventional roles (89.2% vs. 90.7%), but RGRC substantially outperforms it for role-specialized roles (99.1% vs. 78.0%). This split indicates that prompt engineering can approximate rubrics when conventions are well represented in model priors, while professional grounding is essential for standards beyond those priors. FinProBench is built from 1,723 curated deliverables spanning 57 occupations, 8 financial sub-industries, and 161 deliverable types, and releases an initial evaluation set of 20 complete tasks covering 20 roles in 7 sub-industries. With heterogeneous LLM judges and role-level rubrics, human deliverables rank first on average (73.7 vs. 70.3, 70.2, and 69.6 out of 100), while all four systems show overlapping 95% confidence intervals and complementary strengths. Reusing rubrics at the role level reduces estimated per-task construction effort by 6.7 times relative to authoring each rubric from scratch.

Ben Wang, Kang Zhou, Lifan Guo +2

Qwen DianJin Team, Alibaba Cloud Computing

AI Agent Evaluation AI Agent Benchmarks Rubric-Based Evaluation Finance

Aug 4, 2026cs.AI

AgonAlpha: Autonomous Alpha Discovery via Prompt Economy and Scalable Agentic Search

Language models can propose many plausible trading factors, but an autonomous research system must also allocate its evaluation budget, verify its own evidence, and preserve how each candidate was produced. We present AgonAlpha, an architecture that searches over frozen research artifacts---hypotheses, executable expressions, platform evidence, rationales, and review status---rather than formulas alone. To our knowledge, AgonAlpha is the first alpha-mining system to combine verified artifact search, a fresh-context adversarial reviewer with re-execution and veto authority, and pending-aware parallel budget allocation, together with a complete public evidence trail. Independent deployments on WorldQuant BRAIN produced SPECTACULAR-grade alphas across five users and six model backends, with Fitness reaching 9.50 and Sharpe reaching 3.48, while retaining prompt-to-expression provenance for every submission.

Weicheng Ye, Youran Sun, Xingyu Ren +3

Department of Physics, The Chinese University of Hong Kong, Hong Kong SAR, China · Department of Mathematics, University of Maryland, College Park, MD, USA · Department of Computer Science, University of Maryland, College Park, MD, USA

Quantitative Finance Automated Algorithm Discovery Agentic Search Finance Autonomous Research Agents

Aug 4, 2026cs.LG

FinVerse: Financial Time-Series Benchmark

As time-series foundation models have emerged, the need for benchmarks that can evaluate their forecasting ability in meaningful ways has become increasingly important. Existing time-series forecasting benchmarks provide useful standardized comparisons, but they often evaluate heterogeneous series with uniform error-based metrics. Strong performance under such metrics does not necessarily imply that a model's forecasts will support the best real-world decisions across domains. For example, in stock forecasting, correctly predicting whether a price will rise or fall can be more directly relevant to realized returns than minimizing point-wise forecast error alone. To this end, we introduce FinVerse, a finance-domain time-series forecasting benchmark that takes a first step toward more realistic evaluation. The released FinVerse data artifact contains 116,897 financial time series with 171.1M observations, of which 60,232 series with 17.4M observations are selected as evaluated targets based on their economic relevance to financial decisions. Unlike generic forecasting benchmarks that primarily emphasize uniform point-forecast or probabilistic accuracy, FinVerse defines 11 metric families comprising 78 evaluation metrics and assigns the most appropriate evaluation metrics to each individual time series based on its underlying economic meaning. Our analysis of 43 public time-series forecasting foundation models shows that strong performance under generic forecasting criteria does not necessarily translate into useful financial forecasts. This finding highlights the need for domain-aware benchmarks that evaluate models under objectives closer to real-world decision making.

Jaehoon Lee, Jun Seo, Seunghan Lee +9

LG AI Research

Benchmark Design Financial Forecasting Time Series Forecasting Forecasting Benchmarks Financial Time Series Time-Series Foundation Models+1

Aug 4, 2026cs.CL

SeqLLM: Augmenting LLMs with Behavioral-Sequence Modeling for High-Stakes Decisions at WeChat Pay

Merchant risk control at large payment platforms screens tens of millions of merchants daily, where false positives harm legitimate merchants and false negatives leave harmful activity undetected. The hardest cases require jointly understanding a merchant's textual profile and long behavioral sequence. Large language models (LLMs) excel at text but cannot natively model such sequences, while adapting them often causes catastrophic forgetting. We present SeqLLM, a framework that adds behavioral-sequence modeling to a pretrained LLM while preserving its language ability. SeqLLM combines three components: a compact discrete vocabulary that represents behavioral events as native tokens; a lightweight projector, trained with a two-stage alignment curriculum, that grounds these tokens in the LLM's semantic space; and prefix-guided capability injection, which acquires sequence-modeling ability through task-prefixed supervised fine-tuning rather than continual pre-training. SeqLLM is deployed at WeChat Pay, screening millions of merchants daily. Against the production DeepSeek-based LLM baseline, it raises screening precision from 92.0% to 97.5%. Its pretrained behavior-token embeddings also improve [email protected]% by 26.8 percentage points in a production fraud detector serving billion-scale transaction traffic. Beyond payments, SeqLLM achieves state-of-the-art results on public recommendation benchmarks. On MovieLens and Amazon, it surpasses the strong User-LLM baseline by up to 32% relative Recall@5 while retaining markedly stronger language ability. On RecIF, it improves Pass@32 by 14.2% over the full OneRec-8B pipeline using only one-fifth of its GPU-days.

Guilin Li, Jiaxing Zhang, Matthias Hwai Yong Tan +2

Shanghai Jiao Tong University China

Sequential Recommendation Financial Fraud Detection Large Language Model-Based Recommendation LLM Post-Training Finance

Aug 2, 2026cs.CL

Can Language Models Identify Shadow Trading Targets? An NLP Evaluation of SEC Enforcement Theory

Shadow trading -- trading in a peer firm's securities on the basis of material nonpublic information (MNPI) about an "economically linked" company -- is a novel and contested theory of insider trading liability, first prosecuted in SEC v. Panuwat (2023). Enforcing it requires identifying economically linked firms ex ante, a determination the SEC makes only after the fact using mass market surveillance infrastructure. We ask whether NLP can do what the SEC's theory presumes insiders already know: identify peer firms ex ante from publicly mandated disclosures. Using a two-stage LLM pipeline applied to Item 7 (Management's Discussion and Analysis) sections of SEC 10-K filings, we score semantic similarity across 30 M&A events spanning five industries and relate similarity to announcement-day abnormal stock returns. On the Panuwat fact pattern itself the pipeline recovers Incyte among the closest peers, a sanity check on the one case with a known outcome. Across the full dataset, however, we find no association: pooling 217 peer observations, the within-event rank correlation between similarity and abnormal return is +0.07 (permutation p = 0.37), and the mean per-event Spearman correlation is +0.05 with a 95% confidence interval of [-0.08, +0.18] -- narrow enough to exclude any moderate relationship rather than merely failing to detect one. A case-level reading agrees: 14 of 30 events support the hypothesis, 12 contradict it, and 4 are ambiguous. We also find that Incyte fell outside the standard $2B-$10B mid-cap band on the day before the announcement, complicating the "mid-cap oncology" category the SEC invoked. These results are exploratory and bound to this pipeline, corpus, and return measure, but they put pressure on the empirical premise of shadow trading enforcement and bear on constitutional questions surrounding the SEC's financial surveillance infrastructure.

Sarah Wilson, Michael MacKay, Anthony Marello +1

Columbia University.

Aug 2, 2026cs.LG

AlphaG-OPD: Reliability-Gated Sibling Counterfactuals for On-Policy Distillation in Symbolic Alpha Factor Discovery

Symbolic alpha factor discovery can score a completed expression, but it provides no direct label for the structural decisions that produced it. Generative flow networks (GFlowNets) preserve a diverse, reward-proportional distribution over complete expressions, yet their trajectory-level objective does not compare unchosen sibling actions at an intermediate state. We introduce AlphaG-OPD, a structural on-policy distillation framework that turns terminal factor evaluations into local action guidance. Its design separates three decisions. Component I determines where to teach by exposing grammar-valid siblings at partial abstract-syntax-tree (AST) states visited by the current forward policy. Component II determines what is reliable enough to teach: it evaluates three supported siblings under four shared suffixes and admits a KL-bounded target only when their matched comparisons exhibit sufficient winner agreement and a positive empirical lower confidence bound (LCB). Component III determines how strongly and for how long to teach by consolidating accepted targets through bounded replay, score-indexed expiry, and forward-gradient balancing, without additional factor evaluations. Terminal reward, Trajectory Balance, the backward policy, grammar, and factor-pool rules remain unchanged. An equal-physical-score four-arm ablation tests paired teaching, reliability gating, and consolidation. Across China's CSI300, CSI500, and CSI1000 and the U.S. S&P 500, the complete method delivers strong cross-market performance over multiple random seeds.

Yaoyu Su

Quantitative Finance Generative Flow Networks On-Policy Distillation Counterfactual Learning Finance

Aug 2, 2026q-fin.MF

Amortizing the Calibration Triple: A Projection-Consistent Neural Operator for Local-Stochastic Volatility

Local-stochastic volatility (LSV) combines vanilla marginals with richer smile dynamics, but calibration requires a slow, noisy and sequential McKean--Vlasov fixed point. We learn a projection-consistent operator for the calibration triple. Given finite quotes and a stochastic-volatility (SV) backbone, it jointly returns an implied-volatility surface subject to static-arbitrage constraints, its Dupire local volatility, LSV leverage and the conditional moment required by the projection identity. Starting from option-price marginals, we derive a division-free Dupire residual in log-implied-variance coordinates and a quotient Fokker--Planck equation after Gyöngy projection. Deep Operator Network (DeepONet) and Fourier Neural Operator (FNO) implementations enforce quote fit, static-arbitrage, Dupire and projection constraints. For the witness-augmented residual system, we prove conditional identification and empirical consistency under LSV existence and inverse residual stability. In controlled synthetic tests, forward-start and cliquet errors differ from a particle method by 0.1 and 0.2 percentage points, while calibration latency falls from 98.5 to 0.6 ms. Compared with the tested baselines, local-volatility root-mean-square error (RMSE) falls by 36% and leverage RMSE by 7-16%. These results support amortizing the LSV fixed point: the expensive solve moves offline, while online calibration reduces to a single projection-consistent operator evaluation.

Xiaozhen Wang, Anaïs Després, Martin Dureau +1

1CEREMADE, Université Paris Dauphine-PSL · 2LaMME, Université Évry Paris-Saclay · 3AIML Global Markets, Barclays

Quantitative Finance Model Calibration Neural Operators Finance

Aug 2, 2026cs.CL

ShiJianBench: From Dialogue to Decision for Long-Horizon Evaluation of Investment Advisors

Conversational investment advisors influence not only what users know, but also how they make subsequent decisions as market conditions evolve. Existing evaluations primarily assess response quality or observed outcomes, leaving the long-horizon pathway from advisor language to investor behavior difficult to audit. We introduce ShiJianBench, an offline framework for evaluating conversational investment advisors through matched investor trajectories under fixed historical market feedback. At its core is a multi-agent investor simulator with explicit evolving state variables, motive-driven deliberation, long-term memory, and dialogue-grounded updates. The simulator is calibrated against aggregate behavioral patterns from 7,199 real users, and advisor policies are evaluated using separate investor-side, service-side, and content-side metrics under a hard compliance gate. Experiments on Chinese fund-market traces from 2021 to 2026 identify a stable leading group of LLM advisors that combines substantially stronger personalized content with competitive investor-side trajectory outcomes. These results reveal a systematic distinction between producing a high-quality response and delivering an effective long-horizon intervention, motivating trajectory-aware evaluation of conversational advisors.

Jie Gong, Maowei Jiang, Zhiwei Liu +14

School of Artificial Intelligence, Wuhan University · Nanjing Audit University · The University of Manchester +3

Financial Services Long-Horizon Agent Evaluation Agent Evaluation AI Agent Benchmarks Finance Financial Decision-Making

Aug 2, 2026econ.GN

Talking to Digital Twins: Selective Disclosure and Belief Measurement in Financial Social Media

Social media affect financial markets, but public posts by financial media personas are voluntary disclosures. What is not disclosed is therefore usually unobserved. We address this measurement problem by conducting repeated, real-time interviews of "digital twins" built from monitored finfluencers' X accounts under a fixed protocol. The interviews recover stock-level public-persona belief proxies even when no public recommendation is made. Because the interviews are generated and archived before the relevant return windows, the design avoids the look-ahead bias that arises when LLMs are queried ex post. The evidence shows that information obtained from these digital-twin interviews predicts the cross section of large-cap stock returns in the expected direction. Repeated real-time interviews therefore show how selective disclosure can be turned into measurable panels of market views.

Boone Bowles, Raymond Duch, Sorin Sorescu

Mays Business School, Texas A&M University · Nuffield College, University of Oxford

Social Media Analysis Quantitative Finance Finance

Aug 1, 2026cs.AI

FinDeepIndicator: Benchmarking Deep Research Agents in End-to-End Financial Indicator Construction

Financial indicators are essential tools for transforming raw financial data into interpretable measures for various downstream tasks, such as valuation, risk assessment, and economic analysis. However, existing financial benchmarks largely focus on answer-level accuracy and often assume that relevant data are already provided, leaving the assessment of the intermediate process of indicator construction underexplored. In this work, we propose FinDeepIndicator, the first benchmark dedicated to evaluating Deep Research (DR) agents in end-to-end financial indicator construction. Specifically, FinDeepIndicator evaluates DR agents across four stages in indicator construction: formula specification, data collection, indicator calculation, and answer generation, and covers fundamental, technical, and macroeconomic indicators organized into 21 fine-grained sub-categories. It contains 3,350 curated question-answer (QA) pairs derived from both U.S. and Chinese markets, 10 years of historical financial data, and 800 listed companies. Extensive experiments on search-equipped Large Language Models (LLMs) and DR agents show that, while LLMs generally perform well in formula specification, their accuracy drops substantially during data retrieval and numerical execution. DR agents consistently outperform search-equipped LLMs, yet remain unreliable in realistic financial analysis settings. These findings provide insights for developing more capable and trustworthy DR agents in finance.

Chaoqun Yang, Fengbin Zhu, Xinyu Lin +5

School of Computing, National University of Singapore · Institute of Computing Technology, Chinese Academy of Sciences · China Economics and Management Academy, Central University of Finance and Economics +1

Quantitative Finance Deep Research Agents AI Agent Evaluation Finance

Jul 31, 2026cs.CL

Backtrader-Bench: Benchmarking LLM Agents on Algorithmic Trading with Self-Generated MCQs

Evaluating LLM coding agents in algorithmic trading is difficult because static benchmarks risk data contamination and numerical backtest outputs require ground truth from actual code execution. We present Backtrader-Bench, a framework with two complementary pipelines. A deterministic multiple-choice question (MCQ) pipeline generates questions from backtest configurations across five trading strategies, 33 templates, and three difficulty tiers, with an independent checker that re-derives every answer. A generator-solver filtering pipeline autonomously mines harder questions: a generator writes questions verified by executable code, converts them to MCQs, and discards any that a no-tool solver can answer without code execution. We evaluate 11 models without tools (10 runs each) and four with-tools configurations on a 30-question curated set. Tool-augmented agents reach 90.0% accuracy in a single pass (GPT-5.5 and Opus 4.7), outperforming the best no-tools baselines (73.0%, averaged over 10 runs) by 17 percentage points. On 38 separately mined questions, no-tools accuracy drops further, with half the models falling to roughly random-chance level (25%). Beyond evaluation, the scalable MCQ infrastructure is designed to produce a training corpus for reinforcement learning, with the ultimate goal of building a specialized agent for quantitative trading workflows.

Ruoxi Zhao, Maziar Raissi

University of California, Riverside

AI Coding Agents LLM Agent Evaluation AI Agent Benchmarks Finance Algorithmic Trading

Jul 30, 2026cs.CL

Benchmarks Are Not Validation: A System-Level View of Financial LLM Applications

Large language models are increasingly deployed in financial applications that combine retrieval, proprietary data, tool use, orchestration logic, monitoring, and human escalation. Yet evaluation often remains model-centric: benchmark scores, task accuracy, or one-off qualitative reviews are treated as evidence of readiness. In financial settings, this is insufficient. We take the position that financial LLM systems should not be approved for production based on benchmark performance alone. They require system-level validation evidence across the application stack: data, model design, retrieval and generation performance, agent behavior, governance, and implementation. Drawing on industry experience validating GenAI applications in financial institutions, we outline a multi-layer validation view and explain why hybrid evaluation is necessary. We discuss where LLM-as-a-judge methods are useful and why they require controls such as multiple judges, rubrics, agreement, and auditability checks. We also highlight failure modes poorly captured by static benchmarks, including retrieval failures, unfaithful generation, tool misuse, escalation errors, and operational instability. Our position is that financial LLM validation should be an ongoing system discipline rather than a one-time model scoring exercise. Validation should produce decision-ready evidence, not only scores. We conclude with a research agenda for system-aware benchmarks, agent trace validation, judge alignment protocols, and lifecycle validation standards.

Burak Payzun, İrem Demirtaş, Simona Scala +2

Prometeia S.p.A.

Financial Services LLM Evaluation Finance

Jul 30, 2026cs.CL

Beyond Sentiment: Structured Information Extraction from Financial News

Financial sentiment analysis has become a standard component in news-driven stock prediction, yet it reduces rich, multi-dimensional news articles to a single polarity score. We hypothesize that financial news encodes multiple orthogonal information dimensions---event type, impact scope, temporal horizon, and semantic confidence---that sentiment alone cannot capture, and that these dimensions carry independent predictive value. To test this hypothesis, we propose a structured information extraction framework that leverages LLaMA-3.1-70B to extract six semantic dimensions from financial news. Through large-scale experiments on 41,618 news--stock pairs from the FNSPID dataset, we find that (i) FinBERT sentiment features exhibit strong predictive power under nonlinear models (F1=0.576) but substantially weaker performance under linear models (F1=0.230), revealing a highly nonlinear sentiment--return relationship; (ii) LLM-extracted structured features, while individually weaker, capture information orthogonal to sentiment, as evidenced by a 53.5% systematic disagreement rate between the two approaches; and (iii) combining both signal sources yields F1=0.600, significantly outperforming either alone (

p < 0.0001

), with consistent improvements across all seven event types. Ablation experiments confirm that non-sentiment structural dimensions (event type, impact subject, time horizon, confidence) independently contribute

Δ\text{F1} = +0.019

beyond FinBERT alone. Feature importance analysis reveals balanced contributions from all six extracted dimensions (14--21%), demonstrating that compressing news into a single sentiment score incurs substantial information loss. Our results suggest that the sentiment--semantics decoupling in financial text is systematic and exploitable, opening a new direction for multi-dimensional financial NLP.

Daohan Zhu, Sitong Ge, Ruofei Wang +4

School of ASEE, Beihang University, Beijing, China · School of BME, Beihang University, Beijing, China · CAIR and CECS, VinUniversity, Hanoi, Vietnam

Financial Sentiment Analysis Document Information Extraction LLM Information Extraction Finance

Jul 30, 2026cs.CL

CACHE-UK: A Stability-Aware Memory Editor for Sequentially Updated Quantized LLMs in Finance

Large Language Models (LLMs) deployed in dynamic financial environments face a critical challenge: maintaining factual accuracy as market conditions, regulations, and corporate facts change continuously. While 4-bit quantization enables efficient deployment, it severely limits the viability of sequential memory editing: existing methods undergo catastrophic performance degradation under this "quantization stability crisis." We introduce CACHE-UK (Contextual Adaptive Continual Hybrid Editor for UK Finance), a stability-aware memory editing framework specifically designed for domain-specific, quantized LLMs. CACHE-UK integrates three components: a rank-1 LoRA perturbation mechanism that confines edits to the low-rank adapter subspace, a financial domain prioritization module for content-adaptive edit strength, and a closed-loop Stability Controller that tracks "degradation debt" to prevent catastrophic forgetting across sequential updates. Evaluated on a 4-bit quantized OpenLLaMA-3B model with a curated UK financial corpus of 88,021 documents, CACHE-UK reduces knowledge degradation by 11-17% relative to adapted baselines under identical 4-bit constraints -- its most robust effect -- while attaining the highest test success (generalization) rate observed in our setting (28%, a 6 percentage point improvement over the strongest adapted baseline). These results indicate that stability-aware editing can improve factual maintenance in resource-constrained financial LLM deployments, though absolute generalization rates remain low.

Anubhav Lakra, Yue Feng

University of Birmingham, Birmingham, United Kingdom

Knowledge Editing Continual Learning for LLMs Language Modeling Finance Catastrophic Forgetting

Jul 30, 2026cs.CL

FinSMART: Financial Sentiment Analysis for Algorithmic Trading through Market-Aligned Reinforcement Learning

Recent advances in Generative AI have substantially improved financial sentiment analysis through post-trained financial large language models (LLMs). However, existing approaches remain confined to a market-agnostic, supervised learning paradigm that relies on limited, static and human-annotated datasets, and thus are incapable of adapting to evolving market conditions. To address this limitation, we introduce FinSMART, the first market-aligned reinforcement learning framework for financial sentiment analysis, which directly optimizes sentiment signals using realized market outcomes. To deal with the noisy, non-stationary, and multifactorial nature of financial markets, FinSMART incorporates a signal extraction pipeline that combines market-aware data filtering with a discrete asymmetric trading reward, enabling stable reinforcement learning from economically meaningful market feedback. Experimental results demonstrate that FinSMART significantly outperforms existing state-of-the-art methods in profitability, risk-adjusted performance, and sentiment signal quality, improving cumulative trading returns by 220% over the strongest baseline. Uniquely, the FinSMART framework naturally supports market-aware retraining, at any point in time, by replacing costly manual annotation with newly observed financial articles and their realized market outcomes. Such a retraining strategy enables the model to continuously adapt to changing market dynamics, resulting in consistent performance gains over its static counterpart. These findings demonstrate the practical applicability of market-aligned reinforcement learning and highlight its potential as a next-generation paradigm for developing adaptive financial LLMs.

Giorgos Iacovides, Wuyang Zhou, Danilo Mandic

Imperial College London · London, UK

RL for Language Models Reinforcement Learning Financial Sentiment Analysis Finance Algorithmic Trading

Jul 30, 2026cs.CL

FinanceHarness: Autonomous Financial Deep Research Framework

Powered by advances in LLMs and autonomous agents, deep research has become one of the most widely adopted agentic products. However, most deep research systems write general-purpose reports, which are inadequate for financial deep research. Financial research demands specialized knowledge to analyze historical patterns and forecast upcoming events. Automating financial deep research therefore requires both a layered harness to drive the research agent and a verifiable, point-in-time benchmark that prevents leakage of future information. We present FinanceHarness, a harness that runs finance-oriented tools and practitioner-guided workflows, automating financial deep research end to end: environment and data construction, the agent execution loop, and reward modeling. We further propose FinanceGym, comprising thesis-driven research questions and rubrics that combine pre-cutoff and post-cutoff criteria. Professional expert validation yields an 82% pass rate. With the same open-weight backbone, FinanceHarness improves the overall rubric score from 25.3% to 32.4%, demonstrating the effectiveness of our specialized harness design. However, even pairing FinanceHarness with the most cutting edge LLM (e.g. Opus-5), the FinanceGym score is below 45%, showing that it is a challenging benchmark for financial deep research. Leaderboard is available at: https://financegym.github.io/ and FinanceHarness code is available at: https://github.com/Yijia-Xiao/FinanceHarness.

Yijia Xiao, Rujun Han, Yanfei Chen +8

Google Cloud AI Research · University of California, Los Angeles

Deep Research Agents Financial Forecasting LLM Agent Harnesses Finance

Jul 30, 2026cs.CL

AWARE-FX: An Auditable Knowledge-Guided AI System for Measuring Corporate Foreign-Exchange Hedging Disclosure

Corporate annual reports contain weakly structured evidence about foreign-exchange risk management, derivative use, natural hedging, and explicit non-use. This study develops AWARE-FX, an auditable AI/NLP decision-support system that converts report text into traceable firm-year hedging-disclosure measures. The system combines a professional-source lexicon, negation and accounting-status logic, channel-specific financial encoders, exact evidence gates, conservative aggregation, and an audit ledger. Across 24,909 Hong Kong firm-years from 2008-2025, it retrieves and scores 543,527 snippets. Reliability is evaluated through ablations, a stratified 300-snippet human audit, three-seed FinBERT-ModernBERT comparisons, strict 2023-2025 temporal tests, probability calibration, selective prediction, and fixed-prompt generative-model benchmarks. FinBERT has the higher mean F1 in seven of eight encoder task-split comparisons; its temporal F1 ranges from 0.702 to 0.872. Abstaining on the 20% least-confident temporal observations raises retained-sample F1 by 0.050-0.077. Deterministic Qwen3-8B performs strongly on commodity and negation evidence but poorly on foreign-debt and accounting-context labels, showing that a general-purpose LLM does not uniformly replace domain constraints. The strict FX score is negatively associated with linked baseline and stress-period FX exposure, whereas the generic broad score is not. These associations provide external construct validation, not causal estimates of hedging effectiveness. AWARE-FX contributes a tested decision-support architecture in which retrieval, status logic, classification, uncertainty handling, aggregation, and external validation remain separately auditable.

Qi Wang

aUniversity of Nottingham, Nottingham, United Kingdom

Financial Services Document Information Extraction Text Classification Finance

Jul 29, 2026cs.LG

Inverse Learning of Latent Risk-Neutral Densities from Irregular Option Quotes

Accurate option prices do not imply accurate recovery of the latent risk-neutral density. We study this distinction with two complementary benchmarks. A controlled benchmark exposes simulator-truth densities for latent evaluation, while a chronological NIFTY benchmark tests only held-out market prices. A two-component lognormal mixture has the lowest aggregate price,

L^1

, Wasserstein, and fixed-tail errors on the synthetic benchmark. Learned operators retain narrower strengths: DeepONet reduces 1% quantile and variance error by 39.0% and 34.6% relative to the mixture, and a quote transformer reduces

L^1

by 16.4% on the structurally misspecified Merton family. A numerical conditioning analysis explains why these rankings can differ: after enforcing mass and forward constraints, 95 of 126 pricing directions are numerically null, and two densities separated by

L^1 = 0.061

produce identical prices on the covered strikes. On 524 held-out NIFTY calls, validation-selected test-time adaptation reduces DeepONet RMSE by 28.3%, but per-expiry mixture and SVI fits remain much more accurate. The evidence supports target-dependent inductive bias, not a universal winner.

Lennon J. Shikhman, Michael Galarnyk, Aadi Dash +1

School of Computer Science Georgia Institute of Technology USA

Quantitative Finance Deep Operator Networks Density Estimation Neural Operators Inverse Problems Finance

Jul 29, 2026cs.CL

Credit Cards, Confusion, Computation, and Consequences: What Can We Uncover About Language Model Reasoning?

We introduce CreditCardQA, the first financial literacy benchmark for numerical reasoning derived from real credit card agreements. The dataset contains 1,800 questions, including first-person variants that reflect how consumers naturally ask about fees, interest, and payments. We evaluate a range of large language and reasoning models under Chain-of-Thought (CoT) and Program-of-Thought (PoT) prompting. Overall, PoT yields consistent performance gains, particularly for models with weaker baseline reasoning, and narrows gaps between open- and closed-source systems. Through error analysis, we show that failures arise less from arithmetic and more from misapplied financial rules, missed conditions, and misunderstandings of contractual terms. We further analyze question difficulty and find that comparisons, conditional logic, and monetary constraints are especially challenging. We also find that errors often arise in edge cases such as late-payment penalties or small-balance scenarios that are more likely to affect lower-income or financially vulnerable individuals.

Arnav Hiray, Agam Shah, Caleb Lu +3

College of Computing & Scheller College of Business Georgia Institute of Technology, Atlanta, GA

Numerical Reasoning in Language Models Financial Services CoT Reasoning Prompt Engineering Finance

Jul 29, 2026cs.AI

AlphaSchema: Exploring the Space of Trading Semantics for LLM-Based Alpha Mining

Automated alpha mining has increasingly adopted large language model (LLM) agents for factor generation and iterative discovery. However, existing LLM-based systems often delegate both factor construction and search decisions to the agent itself, without an explicit exploration space or a principled mechanism for navigating that space. As a result, exploration remains largely implicit and difficult to control or optimize systematically. We introduce AlphaSchema, which constructs and explores a structured space of trading semantics for alpha mining. Each point in this space is a schema plan composed of Event, Context, Qualities, Direction, and Output, specifying the semantics of a candidate factor before implementation. AlphaSchema decouples exploration from implementation: an LLM translates selected schema plans into executable factors, while evaluated rewards are accumulated to learn a surrogate model over the semantic space. An iterative selection mechanism uses this model to balance global exploration, surrogate-guided exploitation, and local mutation. Experiments on the Chinese stock market show that AlphaSchema discovers factor pools with strong predictive and portfolio performance. Further analyses show that the semantic search process navigates diverse regions while increasingly allocating evaluations toward high-reward regions, and that implementations of the same schema plans by different LLMs exhibit comparable predictive quality, suggesting that alpha mining quality is largely robust to the choice of LLM within our framework.

Jingyang Yi, Jian Yang, Yifei Jin +2

1X-Tech · 2Xtech-PandaAI-Waton Joint Lab · 3Monash University +2

Automated Algorithm Discovery Large Language Model-Guided Optimization Finance Algorithmic Trading

Jul 29, 2026cs.MA

A Persona-based Rate Action Index

We propose an index for predicting the U.S.\ Federal Open Market Committee (FOMC) decision to hike/hold/cut the current federal funds target rate based on how a collection of personas responds to current market conditions. To construct the index, we collected a new dataset consisting of nearly

25{,}000

retrievable chunks from publicly available data. We partition the data into per-member corpora and use each as the retrieval database of a generative system we refer to throughout as a ``persona''. We first evaluate the personas across two complementary components of likeness: identifiability and detectability. Each persona's behavior is highly attributable (average member-conditional recall is

8\times

chance) and generated content is nearly indistinguishable from held-out real content (

\hatτ_{\mathrm{det}} = 0.23

against a

0.15

floor). We then present evidence that query-conditioned representations of the personas capture members' monetary-policy stance relative to a known hawk--dove reputational ordering (Kendall's

τ= 0.63

,

p < 0.001

), substantially outperforming retrieval-only representations. These representations vary with time and current market conditions and form the basis of our proposed persona-based rate action index. For the

2022

--

2025

period the index tracks the rate cycle (Kendall's

τ= 0.68

,

p < 10^{-6}

) and can be used to construct a simple classifier that predicts per-meeting outcomes at non-trivial accuracy (

0.69

versus a

0.47

base rate). Importantly, the index outperforms informative baselines and leads the federal funds target rate by roughly three quarters. As far as we are aware, our results are the first to demonstrate the ability to capture time-varying group behavior via a collection of digital personas.

Hayden Helm, Andrew Dassori

Helivan · Wavelength Capital

Personality Modeling in Language Models Time Series Forecasting Persona-Conditioned Generation Finance Financial Decision-Making

Jul 28, 2026cs.AI

Everyone is unique: Towards Behaviorally Heterogeneous Negotiation Dialogue Systems for Debt Collection

Debt collection is a critical negotiation task in the financial industry, with strong practical relevance and exceptional academic value as a behaviorally rich, high-stakes testbed for human-centered dialogue systems. While large language models (LLMs) have shown promise in dialogue and negotiation, effectively evaluating their performance in this complex scenarios remains a major challenge: existing benchmarks uniformly assume users to be static, rational agents with fixed preferences, failing to capture the rich behavioral heterogeneity inherent in real-world debt collection. To bridge this gap, we propose DebtBench, the first public persona-enriched debt collection benchmark, that highlights behavioral heterogeneity in negotiation. Moreover, we develop DebtGPT, a debt collection agent trained to jointly optimize financial recovery and interaction experience. Our experimental results, using 16 state-of-the-art LLMs, find that most existing models struggle in this complex but realistic scenarios, whereas DebtGPT outperforms all open-source baselines and achieves performance on par with GPT-4o. The code and data are available at https://github.com/YYuHhhh/DebtNegotiation.

Yuhang Yang, Kai Tang, Chao Ye +4

1State Key Laboratory of Blockchain and Data Security, Zhejiang University · 2Ant Group

Automated Negotiation LLM Agent Evaluation Task-Oriented Dialogue Systems Finance

Jul 28, 2026q-fin.CP

RIDGE: An Autonomous Framework for Validation and Method Discovery in LLM-Generated Option Pricing

Automated code generation is becoming an important tool in quantitative finance, where large language models can generate option pricing implementations directly from mathematical model specifications. Validating such implementations, however, requires considerably more than conventional software testing: numerical pricing methods must remain mathematically consistent, numerically stable, and reliable across a wide range of model parameters. We introduce RIDGE, an autonomous validation framework in which generated pricing implementations are subjected to structured no-arbitrage tests, stress tests, benchmark comparisons, and consistency checks. Validation evidence is interpreted diagnostically, while the resulting knowledge is accumulated in a repository and reused across models and successive validation iterations. This enables systematic refinement of both the pricing implementation and the validation methodology. The framework is applied to five stochastic volatility models. Across these studies, all detected implementation defects are removed and, in two cases, the validation process reveals methodological limitations and motivates the development of alternative numerical methods. The supplementary material is available in the GitHub repository: https://github.com/ShQiangLiu/ridge.

Liexin Cheng, Xue Cheng, Shuaiqiang Liu +1

Mathematical Institute, Utrecht University · School of Mathematical Sciences, Peking University · Delft Institute of Applied Mathematics, Delft University of Technology

Quantitative Finance Code Generation Evaluation Finance

Jul 27, 2026cs.LG

GAUGE: Grading Agent-Built Financial Models Without a Golden Answer

Financial models combine public disclosures with analyst assumptions to produce forecasts and valuations. While some components can be checked mechanically, forecasts, discount rates, and target prices often admit multiple reasonable answers. Existing benchmarks nevertheless tend to grade such outputs against a single expert reference. Using independently built analyst models for the same companies, we find that across 108 directed pairs covering 65 companies, the median single-reference score is 0.33, 92.6% score below 0.70, and no same-vintage pair agrees on implied price within 10%. Point-tolerance grading can therefore penalize disagreement already present among professionals. We introduce GAUGE, a benchmark for evaluating agent-built valuation models against observed analyst practice rather than a single point answer. GAUGE uses 1,001 vendor-classified analyst workbooks and a 196-task evaluation set, with a three-layer observed-practice envelope, 56 auditable facets, eight validity gates, and deterministic structural checks. We validate the benchmark with a 55-participant known-groups study, company-grouped cross-fitting, and judge-stability audits. On the failure-aware score

φ_0

, senior analysts average 88.3, juniors 66.0, and finance students 43.2. Across 24 agents and 1,011 scored generations, the best agent scores 53.4, above the student mean but below every senior and most juniors. It passes 93% of mechanical facets and 78% of judgment facets, with a fleet-median gap of 26 points. Current agents are substantially stronger at model construction than valuation judgment. We release the methodology, a gated de-identified data tier, a controlled training split, a versioned 48-task evaluation core, and a withheld refresh pool.

Jiacheng Lu, Sinuo Wang, Wentao Zhao +12

Shanghai Jiao Tong University Shanghai, China · StepFun Shanghai, China · University of Adelaide Adelaide, Australia +5

Quantitative Finance Financial Forecasting AI Agent Evaluation AI Agent Benchmarks Automated Evaluation Finance

Jul 27, 2026cs.CL

INS-ActBench: A Comprehensive Benchmark for Assessing Professional Actuarial Capability of Large Language Models

Large Language Models (LLMs) have shown strong potential in financial reasoning, but existing benchmarks often evaluate domain knowledge, numerical reasoning, long-context understanding, and tool use in separate settings. This limits their ability to assess realistic professional workflows that require auditable, context-grounded, and tool-executable decisions. We introduce \textbf{INS-ActBench}, a comprehensive benchmark for evaluating professional actuarial capability in LLMs. INS-ActBench contains 12,050 Q&A pairs from public exams and sample questions released by 16 actuarial associations. It covers three subsets: \textbf{INS-Act-Know} for standardized actuarial knowledge, \textbf{INS-Act-Case} for long-context insurance case reasoning, and \textbf{INS-Act-Practice} for spreadsheet and R-code tasks with verifiable numerical outputs. Experiments on nine representative LLMs and human actuarial experts reveal a clear capability boundary: frontier LLMs perform strongly on standardized knowledge, but remain much weaker in case reasoning, tool-based workflows, and jurisdiction-sensitive practice. INS-ActBench provides a reproducible foundation for developing actuarial LLMs toward reliable professional assistance. The code is available at https://github.com/FDU-INS/INS-ActBench.

Changyu Chen, Chenwei Lin, Xian Xu

Fudan University

Numerical Reasoning in Language Models LLM Evaluation LLM Tool Use Finance

Jul 27, 2026cs.LG

MAPLE: Efficient and Diverse Multi-Alpha Generation for Portfolio Construction

Classical alpha mining achieves strong risk-adjusted returns by combining many low-correlated predictive signals, yet deep learning stock-ranking methods typically produce a single alpha per stock, rely on increasingly complex architectures with diminishing gains, and obtain diversity only through separate models or implicit routing, without explicitly controlling inter-alpha correlation. We introduce MAPLE (Multi-Alpha Position-aware Listwise Ensembling), a backbone-agnostic framework that recovers this diversity principle within a single training pass. MAPLE combines a unified, capacity-scaled prediction head with an extreme-rank weighted listwise ranking loss and a diversity regularizer that explicitly penalizes pairwise correlation across alphas. Across four equity markets spanning the US, China, and Japan, MAPLE achieves the best average Sharpe and Calmar ratios among nine baselines, using up to 55x fewer parameters and 2.5x less training time, and generalizes across five backbone architectures with Sharpe and Calmar Ratio gains of 10-23% and 17-43%, respectively. Behavioral analysis further shows why each component works: the unified head already reduces inter-alpha correlation before any diversity loss is applied, and the extreme-rank loss lets diversity regularization improve rather than erode per-alpha ranking quality as capacity scaling sustains this balance at scale. These results show that principled loss design and capacity allocation, rather than architectural complexity, drive diverse and effective multi-alpha generation.

Yu-Chen Den, Kuan-Yu Chen, Kendro Vincent +1

SinoPac Holdings · Taipei, Taiwan · National Chengchi University

Learning to Rank Ensemble Learning Portfolio Optimization Finance

Jul 27, 2026cs.LG

FinAbstain: Uncertainty-Calibrated Multimodal RAG for Selective Financial Forecasting

Large language models (LLMs) can synthesize financial narratives but may express high confidence when evidence is sparse, stale, or contradictory. This failure is especially consequential in forecasting, where filings, news, prices, volume, and technical signals can disagree. We present FinAbstain, a research framework for uncertainty-calibrated multimodal retrieval-augmented generation (RAG) with selective prediction. A point-in-time retriever admits only information public at the forecast timestamp and supplies modality-specific evidence to fundamental, news, technical, risk, and verification agents. Their probabilistic assessments are aggregated with retrieval relevance, evidence contradiction, repeated-sample consistency, and historical calibration statistics. Temperature scaling, isotonic regression, conformal prediction, and a proposed hybrid uncertainty score are evaluated under a common chronological protocol. A controller predicts bullish, bearish, or neutral outcomes only when uncertainty is below a validated threshold; otherwise it abstains, requests evidence, reduces exposure, or routes the case to human review. The evaluation covers one- and five-day abnormal-return direction, twenty-day volatility intervals, and abstention decisions, using accuracy, calibration, risk--coverage, citation, trading, latency, and cost metrics. To make the design auditable before a full data collection is complete, we report explicitly labeled simulated results rather than empirical claims. These results illustrate the intended hypothesis: calibrated abstention may trade coverage for lower selective error and drawdown. The contribution is a time-safe architecture, a composite uncertainty formulation, and a reproducible evaluation blueprint for evidence-grounded selective financial forecasting.

Dorothy Torres, Wei Cheng, Henan Huang

School of Science, Technology, Engineering and Mathematics 263 Academy Street, Room S204 Jersey City, NJ 07306 · School of Electrical Engineering and Computer Science The Pennsylvania State University 207 Electrical Engineering West University Park, PA 16802, USA

Selective Prediction Financial Forecasting LLM-Based Time Series Forecasting Retrieval-Augmented Time Series Forecasting Uncertainty Calibration Finance

Jul 26, 2026cs.CL

Earnings25: A Comprehensive 500-Hour Speech Benchmark for Finance

We introduce Earnings25, a finance-domain benchmark for evaluating automatic speech recognition (ASR) on English-language earnings calls under realistic conditions. Earnings25 comprises two complementary test sets: (i) testset-full, 498 hours of full English-language S&P 500 earnings calls from Q4 2025, and (ii) testset-segmented, a 46-hour industry-balanced set of 290 segments sampled from English-language U.S. earnings calls in 2025. The benchmark provides aligned transcripts and structured metadata, including speaker roles, industry labels, and call structure, enabling speaker- and industry-aware evaluation beyond aggregate word error rate (WER). We report reproducible baselines for Whisper and Parakeet-TDT using standardized scoring.

Denglin Jiang, Haoran Zhou, Anshul Wadhawan +7

Bloomberg, United States

ASR Evaluation Automatic Speech Recognition Finance

Jul 26, 2026cs.LG

Extreme Volatility Warning under Label Scarcity via Multi-Source Anomaly Fusion

Early warning of extreme market volatility is central to financial risk management, but actionable events are rare, nonstationary, and often triggered by exogenous information shocks. In our CSI300 setting, only $\sim$ 80 positive samples are observed across 791 training days, making heavily supervised multi-source models unstable. We first analyze a 100K-parameter hierarchical text-signal fusion model (HTSF) and find that added parameterization hurts in this low-label regime. Motivated by this failure, we propose \textbf{AAMSF} (Anomaly-Augmented Multi-Signal Fusion), a semisupervised framework that combines Isolation Forest anomaly scores over market indicators, GDELT events, Chinese financial news, and English media with lightweight Ridge score fusion. We further introduce \textbf{T-AAMSF}, a temporal extension for multi-day anomaly accumulation. On CSI300 (2018--2023), AAMSF achieves test AUC-ROC \textbf{0.680}, outperforming the strongest unsupervised baseline (0.630) and neural baseline (0.588), while T-AAMSF improves PR-AUC to 0.291. Ablations reveal strong source asymmetry: GDELT and domestic financial news provide complementary risk signals, whereas English media consistently reduces performance, and learned weighting is unreliable under validation noise. These results suggest an empirical design principle for label-scarce financial risk warning: robust anomaly geometry and source reliability can matter more than supervised representation capacity.

Jin Qian, Zhangzhi Xiong, Mingrui Li +1

ShanghaiTech University, Shanghai, China

Multimodal Anomaly Detection Financial Time Series Finance Anomaly Detection