Finance

We introduce a multi-agent framework intended to emulate parts of a quantitative research team and support equity factor research on large financial panel datasets. QRAFTI integrates a research toolkit for panel data with MCP servers that expose data access, factor construction, and custom coding operations as callable tools. It can help replicate established factors, formulate and test new signals, and generate standardized research reports accompanied by narrative analysis and computational traces. On multi-step empirical tasks, using chained tool calls and reflection-based planning may offer better performance and explainability than dynamic code generation alone.

High-fidelity, scalable market simulation is a key instrument for mechanism evaluation, stress testing, and counterfactual policy analysis. Yet existing simulators rarely achieve mechanism fidelity beyond single-asset intraday settings, microstructure fidelity against historical limit order books (LOB), and computational tractability at market scale in a single system. This paper presents EvoMarket, a discrete-event, multi-agent financial market simulator designed for intervention-oriented experiments in multi-asset and cross-day environments. EvoMarket couples a high-throughput execution core (optimized LOB data structures, hierarchical scheduling under propagation delays, and asynchronous per-asset matching) with explicit institutional mechanisms (market calendars, opening call auctions, price limits, and T+1 settlement). To avoid expensive black-box calibration, EvoMarket introduces an Oracle-guided in-run self-calibration mechanism that interprets microstructure discrepancy as missing order flow and synthesizes corrective orders at recording checkpoints. Experiments on China A-share order-flow and LOB data show close replay alignment over five trading days, fidelity gains from budgeted in-run calibration across depth levels, broad agent order-space coverage, and scalable performance under increasing input order rates and market breadth. We further demonstrate cross-asset linkage and event-study style intervention evaluation that produces structured dependence and interpretable event-time responses.

We present the first portfolio-level validation of MarketSenseAI, a deployed multi-agent LLM equity system. All signals are generated live at each observation date, eliminating look-ahead bias. The system routes four specialist agents (News, Fundamentals, Dynamics, and Macro) through a synthesis agent that issues a monthly equity thesis and recommendation for each stock in its coverage universe, and we ask two questions: do its buy recommendations add value over both passive benchmarks and random selection, and what does the internal agent structure reveal about the source of the edge? On the S&P 500 cohort (19 months) the strong-buy equal-weight portfolio earns +2.18%/month against a passive equal-weight benchmark of +1.15% (approximating RSP), a +25.2% compound excess, and ranks at the 99.7th percentile of 10,000 Monte Carlo portfolios (p=0.003). The S&P 100 cohort (35 months) delivers a +30.5% compound excess over EQWL with consistent direction but formal significance not reached, limited by the small average selection of ~10 stocks per month. Non-negative least-squares projection of thesis embeddings onto agent embeddings reveals an adaptive-integration mechanism. Agent contributions rotate with market regime (Fundamentals leads on S&P 500, Macro on S&P 100, Dynamics acts as an episodic momentum signal) and this agent rotation moves in lockstep with both the sector composition of strong-buy selections and identifiable macro-calendar events, three independent views of the same underlying adaptation. The recommendation's cross-sectional Information Coefficient is statistically significant on S&P 500 (ICIR=+0.489, p=0.024). These results suggest that multi-agent LLM equity systems can identify sources of alpha beyond what classical factor models capture, and that the buy signal functions as an effective universe-filter that can sit upstream of any portfolio-construction process.

Sparsity or complexity? In modern high-dimensional asset pricing, these are often viewed as competing principles: recent empirical evidence favors richer models, while economic intuition has long favored parsimony. We reconcile this tension by distinguishing capacity sparsity-restrictions on effective model capacity-from factor sparsity-the parsimonious structure of priced risks. Revisiting the benchmark empirical design of Didisheim et al. (2025), we combine nonlinear feature expansions with basis pursuit, using column generation and GPU acceleration to scale estimation to 432 million candidate factors. Reaching this scale reveals a reversal in out-of-sample performance: sparse portfolios trail dense ridgeless benchmarks at lower complexity but achieve a higher Sharpe ratio and lower pricing error at the largest candidate set. Capacity expansion and factor sparsity are therefore complements: enlarging the candidate space allows a parsimonious pricing kernel to outperform its dense counterpart.

Recent deployments of large language models (LLMs) as autonomous trading agents raise questions about whether financial decision-making competence generalizes beyond specific market patterns and how it should be trained and evaluated in noisy markets lacking ground truth. We propose a structured framework for training and evaluating such models. Central to our approach is a curated, multiple-choice question (MCQ) dataset derived from classic textbooks and historical markets, verified by an AI committee, enriched with structured reasoning traces, and augmented to reduce shortcut learning. To evaluate whether performance on isolated MCQs generalizes to real-world trading, we introduce a two-stage protocol combining test-set evaluation with an MCQ-based chronological trading simulation. Extensive evaluations across market regimes provide statistically robust evidence that open models trained with our framework exhibit competitive, risk-aware behavior over time, outperform open-source baselines, and approach frontier-model performance at smaller scale. We release the dataset and evaluation framework to support further research.

We introduce JFinTEB, the first comprehensive benchmark specifically designed for evaluating Japanese financial text embeddings. Existing embedding benchmarks provide limited coverage of language-specific and domain-specific aspects found in Japanese financial texts. Our benchmark encompasses diverse task categories including retrieval and classification tasks that reflect realistic and well-defined financial text processing scenarios. The retrieval tasks leverage instruction-following datasets and financial text generation queries, while classification tasks cover sentiment analysis, document categorization, and domain-specific classification challenges derived from economic survey data. We conduct extensive evaluations across a wide range of embedding models, including Japanese-specific models of various sizes, multilingual models, and commercial embedding services. We publicly release JFinTEB datasets and evaluation framework at https://github.com/retarfi/JFinTEB to facilitate future research and provide a standardized evaluation protocol for the Japanese financial text mining community. This work addresses a critical gap in Japanese financial text processing resources and establishes a foundation for advancing domain-specific embedding research.

The proliferation of financial misinformation poses a severe threat to market stability and investor trust, misleading market behavior and creating critical information asymmetry. Detecting such misleading narratives is inherently challenging, particularly in real-world scenarios where external evidence or supplementary references for cross-verification are strictly unavailable. This paper presents our winning methodology for the "Reference-Free Financial Misinformation Detection" shared task. Built upon the recently proposed RFC-BENCH framework (Jiang et al. 2026), this task challenges models to determine the veracity of financial claims by relying solely on internal semantic understanding and contextual consistency, rather than external fact-checking. To address this formidable evaluation setup, we propose a comprehensive framework that capitalizes on the reasoning capabilities of state-of-the-art Large Language Models (LLMs). Our approach systematically integrates in-context learning, specifically zero-shot and few-shot prompting strategies, with Parameter-Efficient Fine-Tuning (PEFT) via Low-Rank Adaptation (LoRA) to optimally align the models with the subtle linguistic cues of financial manipulation. Our proposed system demonstrated superior efficacy, successfully securing the first-place ranking on both official leaderboards. Specifically, we achieved an accuracy of 95.4% on the public test set and 96.3% on the private test set, highlighting the robustness of our method and contributing to the acceleration of context-aware misinformation detection in financial Natural Language Processing. Our models (14B and 32B) are available at https://huggingface.co/KaiNKaiho.

Synthetic augmentation is increasingly used to mitigate data scarcity in financial machine learning, yet its statistical role remains poorly understood. We formalize synthetic augmentation as a modification of the effective training distribution and show that it induces a structural bias--variance trade-off: while additional samples may reduce estimation error, they may also shift the population objective whenever the synthetic distribution deviates from regions relevant under evaluation. To isolate informational gains from mechanical sample-size effects, we introduce a size-matched null augmentation and a finite-sample, non-parametric block permutation test that remains valid under weak temporal dependence. We evaluate this framework in both controlled Markov-switching environments and real financial datasets, including high-frequency option trade data and a daily equity panel. Across generators spanning bootstrap, copula-based models, variational autoencoders, diffusion models, and TimeGAN, we vary augmentation ratio, model capacity, task type, regime rarity, and signal-to-noise. We show that synthetic augmentation is beneficial only in variance-dominant regimes, such as persistent volatility forecasting-while it deteriorates performance in bias-dominant settings, including near-efficient directional prediction. Rare-regime targeting can improve domain-specific metrics but may conflict with unconditional permutation inference. Our results provide a structural perspective on when synthetic data improves financial learning performance and when it induces persistent distributional distortion.

We study a speculative trading problem within the exploratory reinforcement learning (RL) framework of Wang et al. [2020]. The problem is formulated as a sequential optimal stopping problem over entry and exit times under general utility function and price process. We first consider a relaxed version of the problem in which the stopping times are modeled by the jump times of Cox processes driven by bounded, non-randomized intensity controls. Under the exploratory formulation, the agent's randomized control is characterized via the probability measure over the jump intensities, and their objective function is regularized by Shannon's differential entropy. This yields a system of the exploratory HJB equations and Gibbs distributions in closed-form as the optimal policy. Error estimates and convergence of the RL objective to the value function of the original problem are established. Finally, an RL algorithm is designed, and its implementation is showcased in a pairs-trading application.

Statistical fairness metrics in AI-driven credit decisions conflate two causally distinct mechanisms: discrimination operating directly from a protected attribute to a credit outcome, and structural inequality propagating through legitimate financial features. We formalise this distinction using Pearl's framework of natural direct and indirect effects applied to the credit decision setting. Our primary theoretical contribution is an identification strategy for natural direct and indirect effects under treatment-induced confounding -- the prevalent setting in which protected attributes causally affect both financial mediators and the final decision, violating standard sequential ignorability. We show that interventional direct and indirect effects (IDE/IIE) are identified under the weaker Modified Sequential Ignorability assumption, and prove that IDE/IIE provide conservative bounds on the unidentified natural effects under monotone indirect treatment response. We propose a doubly-robust augmented inverse probability weighted (AIPW) estimator for IDE/IIE with semiparametric efficiency properties, implemented via cross-fitting. An E-value sensitivity analysis addresses residual confounding on the direct pathway. Empirical evaluation on 89,465 real HMDA conventional purchase mortgage applications from New York State (2022) demonstrates that approximately 77% of the observed 7.9 percentage-point racial denial disparity operates through financial mediators shaped by structural inequality, while the remaining 23% constitutes a conservative lower bound on direct discrimination. The open-source CausalFair Python package implements the full pipeline for deployment at resource-constrained financial institutions.

Retrieval-Augmented Generation (RAG) systems for financial document QA typically follow a chunk-based paradigm: documents are split into fragments, embedded, and retrieved by similarity. In structurally homogeneous corpora such as regulatory filings, this suffers from cross-document chunk confusion. Semantic File Routing (SFR), which uses LLM structured output to route queries to whole documents, reduces catastrophic failures but sacrifices targeted-chunk precision. We identify this robustness-precision trade-off on the FinDER benchmark (1,500 queries across five groups): SFR achieves higher average scores (6.45 vs. 6.02) and fewer failures (10.3% vs. 22.5%), while chunk-based retrieval (CBR) yields more perfect answers (13.8% vs. 8.5%). To resolve it, we propose Hybrid Document-Routed Retrieval (HDRR), a two-stage architecture that uses SFR as a document filter followed by chunk retrieval scoped to the identified document(s), eliminating cross-document confusion while preserving chunk precision. HDRR achieves the best performance on every metric: an average score of 7.54 (25.2% above CBR, 16.9% above SFR), a 6.4% failure rate, 67.7% correctness (+18.7 pp over CBR), and a 20.1% perfect-answer rate (+6.3 pp over CBR, +11.6 pp over SFR), simultaneously attaining the lowest failure rate and highest precision across all five groups. Beyond accuracy, HDRR is also the most efficient of the high-quality systems: it preserves CBR's compact per-query token budget (~5K-15K, an order of magnitude below SFR's ~50K-200K), incurs no indexing-time LLM spend (versus the one-time ~$100 cost of contextual indexing), and uses fewer per-query LLM calls than self-correcting agentic baselines, translating directly to lower API spend and inference-time energy at deployment scale.

Large language models are increasingly used to generate financial alpha signals, but many have memorized the historical data in their training corpora, producing apparent accuracy that collapses out of sample. Membership inference attacks (MIA) have been proposed as a diagnostic. What has not been established is whether MIA scores are informative about memorization in this setting, or whether signal-level filtering built on them helps once realistic costs are applied.We introduce MemGuard-Alpha, comprising a composite contamination score combining five MIA methods with a temporal proximity feature, and Cross-Model Memorization Disagreement, which exploits variation in training cutoffs across models. We then audit both. Across seven LLMs (124M-7B), 50 S&P 100 constituents, 42,800 prompts and 299,600 prompt-model MIA scores spanning 2019-2024, three findings emerge.First, where in-sample status is defined by a training cutoff, a temporal proximity feature recovers that label perfectly (ROC-AUC 1.000) because it is a monotone transform of the defining variable; any composite score containing such a feature reports separation that is arithmetic rather than detection. Second, the discriminative power of the MIA scores is largely attributable to scale differences between models: asked at a fixed date which models had that date in training, raw scores appear highly informative (AUC up to 0.99), but under three independent within-model normalizations discrimination falls to 0.487-0.537. Third, with transaction costs applied symmetrically, no filtering variant improves risk-adjusted performance over the unfiltered ensemble, none attains significant Fama-French five-factor alpha, and excluding the single weakest model outperforms every contamination-based filter.We report these as negative results with the failure modes that produced them, and release all artifacts needed to reproduce them.

We introduce a new agentic artificial intelligence (AI) platform for portfolio management. Our architecture consists of three layers. First, two large language model (LLM) agents are assigned specialized tasks: one agent screens for firms with desirable fundamentals, while a sentiment analysis agent screens for firms with desirable news. Second, these agents deliberate to generate and agree upon buy and sell signals from a large portfolio, substantially narrowing the pool of candidate assets. Finally, we apply a high-dimensional precision matrix estimation procedure to determine optimal portfolio weights. We show, through information acquisition theory, that screening with agentic AI can bring utility gains in screening compared with humans. We introduce the concept of sensible screening and establish that, under mild screening errors, the squared Sharpe ratio of the screened portfolio consistently estimates its target. Empirically, our method achieves superior Sharpe ratios relative to an unscreened baseline portfolio and to conventional screening approaches, evaluated on S&P~500 data over both short and medium terms.

We show that AI-driven investment strategies are inherently self-defeating at scale. As AI adoption rises, three mutually reinforcing channels -- signal crowding, performative signal erosion, and Red Queen competition -- compress excess returns. We derive the alpha half-life $h(φ) = \ln 2/[θ+ δ(φ)]$, where $θ$ is the natural mean-reversion rate and $δ(φ) = Nφρa/λ(φ)$ is the AI-accelerated decay component, which is convex-decreasing in adoption. At current adoption levels ($φ\approx 0.7$, $ρ\approx 0.6$), the model implies signal half-lives of 18 months versus 5-7 years pre-AI. We establish four theoretical results. First, the alpha half-life theorem: signal lifespans are convex-decreasing in AI adoption. Second, a signal extinction cascade: beyond a critical threshold $φ^*$, the decay of one signal class triggers accelerated competition for remaining signals. Third, a Red Queen impossibility: in the monoculture equilibrium, net alpha is identically zero despite heavy AI investment. Fourth, a fragility-efficiency tradeoff: the adoption level maximizing price discovery strictly exceeds the level minimizing systemic fragility. Empirical validation calibrates portfolio convergence to SEC Form 13F filing patterns (99.5 million holdings, 2013-2024), documenting that simulated institutional portfolio convergence increases by 42% over the sample period. We examine simulated hedge fund return dynamics showing declining cross-sectional dispersion among AI-adopting funds, and simulate the 2010 Flash Crash to illustrate fragility consequences.

As artificial intelligence and generative large language models drive industrial upgrading, capital markets increasingly focus on AI-themed listed firms. Information asymmetry and technological opacity lower the cost of exaggerating AI capabilities relative to genuine R&D, spurring widespread AI Washing. Using China's A-share market from 2018Q1 to 2025Q2, we advance literature in measurement and mechanism testing. We construct a multimodal AI Washing Risk Score (AWRS) via Qwen-VL to assess text-image consistency in annual reports and roadshows, and a Material Real-Investment Matching Index (MRMI) from patent quality, AI intangible asset capitalization, and technical personnel compensation using PCA. Four findings emerge: (1) AWRS lacks predictive power for future MRMI, with a wider rhetoric-action gap among financially constrained firms; (2) substantive AI investment boosts high-quality patents, while empty rhetoric crowds out industry innovation; (3) long-horizon institutional investors detect AI Washing through site visits and reduce holdings; (4) such divestment triggers analyst downgrades, retail selling, and sharp valuation corrections within 180 days. Results are robust to IV-2SLS and staggered DID using the ChatGPT shock. This study enhances disclosure and pricing-efficiency research and supports RegTech for curbing thematic speculation.

Applying reinforcement learning (RL) to foreign exchange (Forex) trading remains challenging because realistic environments, well-defined reward functions, and expressive action spaces must be satisfied simultaneously, yet many prior studies rely on simplified simulators, single scalar rewards, and restricted action representations, limiting both interpretability and practical relevance. This paper presents a modular RL framework designed to address these limitations through three tightly integrated components: a friction-aware execution engine that enforces strict anti-lookahead semantics, with observations at time t, execution at time t+1, and mark-to-market at time t+1, while incorporating realistic costs such as spread, commission, slippage, rollover financing, and margin-triggered liquidation; a decomposable 11-component reward architecture with fixed weights and per-step diagnostic logging to enable systematic ablation and component-level attribution; and a 10-action discrete interface with legal-action masking that encodes explicit trading primitives while enforcing margin-aware feasibility constraints. Empirical evaluation on EURUSD focuses on learning dynamics rather than generalization and reveals strongly non-monotonic reward interactions, where additional penalties do not reliably improve outcomes; the full reward configuration achieves the highest training Sharpe (0.765) and cumulative return (57.09 percent). The expanded action space increases return but also turnover and reduces Sharpe relative to a conservative 3-action baseline, indicating a return-activity trade-off under a fixed training budget, while scaling-enabled variants consistently reduce drawdown, with the combined configuration achieving the strongest endpoint performance.

Stock markets exhibit regime-dependent behavior where prediction models optimized for stable conditions often fail during volatile periods. Existing approaches typically treat all market states uniformly or require manual regime labeling, which is expensive and quickly becomes stale as market dynamics evolve. This paper introduces an adaptive prediction framework that adaptively identifies deviations from normal market conditions and routes data through specialized prediction pathways. The architecture consists of three components: (1) an autoencoder trained on normal market conditions that identifies anomalous regimes through reconstruction error, (2) dual node transformer networks specialized for stable and event-driven market conditions respectively, and (3) a Soft Actor-Critic reinforcement learning controller that adaptively tunes the regime detection threshold and pathway blending weights based on prediction performance feedback. The reinforcement learning component enables the system to learn adaptive regime boundaries, defining anomalies as market states where standard prediction approaches fail. Experiments on 20 S&P 500 stocks spanning 1982 to 2025 demonstrate that the proposed framework achieves 0.68% mean absolute percentage error (MAPE) for one-day predictions without the reinforcement controller and 0.59% MAPE with the full adaptive system, compared to 0.80% for the baseline integrated node transformer. Directional accuracy reaches 72% with the complete framework. The system maintains robust performance during high-volatility periods, with MAPE below 0.85% when baseline models exceed 1.5%. Ablation studies confirm that each component contributes meaningfully: autoencoder routing accounts for 36% relative MAPE degradation upon removal, followed by the SAC controller at 15% and the dual-path architecture at 7%.

Large Language Models (LLMs) are rapidly transitioning from static Natural Language Processing (NLP) tasks including sentiment analysis and event extraction to acting as dynamic decision-making agents in complex financial environments. However, the evolution of LLMs into autonomous financial agents faces a significant dilemma in evaluation paradigms. Direct live trading is irreproducible and prone to outcome bias by confounding luck with skill, whereas existing static benchmarks are often confined to entity-level stock picking and ignore broader market attention. To facilitate the rigorous analysis of these challenges, we introduce CN-Buzz2Portfolio, a reproducible benchmark grounded in the Chinese market that maps daily trending news to macro and sector asset allocation. Spanning a rolling horizon from 2024 to mid-2025, our dataset simulates a realistic public attention stream, requiring agents to distill investment logic from high-exposure narratives instead of pre-filtered entity news. We propose a Tri-Stage CPA Agent Workflow involving Compression, Perception, and Allocation to evaluate LLMs on broad asset classes such as Exchange Traded Funds (ETFs) rather than individual stocks, thereby reducing idiosyncratic volatility. Extensive experiments on nine LLMs reveal significant disparities in how models translate macro-level narratives into portfolio weights. This work provides new insights into the alignment between general reasoning and financial decision-making, and all data, codes, and experiments are released to promote sustainable financial agent research.

Adapting large language models (LLMs) to specialized financial reasoning typically requires expensive fine-tuning that produces model-locked expertise. Training-free alternatives have emerged, yet our experiments show that leading methods (GEPA and ACE) achieve only marginal gains on the FAMMA financial reasoning benchmark, exposing the limits of unstructured text optimization for complex, multi-step domain reasoning. We introduce Automated Skill Distillation and Adaptation (ASDA), a framework that automatically generates structured skill artifacts through iterative error-corrective learning without modifying model weights. A teacher model analyzes a student model's failures on financial reasoning tasks, clusters errors by subfield and error type, and synthesizes skill files containing reasoning procedures, code templates, and worked examples, which are dynamically injected during inference. Evaluated on FAMMA, ASDA achieves up to +17.33% improvement on arithmetic reasoning and +5.95% on non-arithmetic reasoning, substantially outperforming all training-free baselines. The resulting skill artifacts are human-readable, version-controlled, and compatible with the Agent Skills open standard, offering any organization with a labeled domain dataset a practical and auditable path to domain adaptation without weight access or retraining.

Federal Open Market Committee (FOMC) statements are a major source of monetary-policy information, and even subtle changes in their wording can move global financial markets. A central task is therefore to measure the hawkish--dovish stance conveyed in these texts. Existing approaches typically treat stance detection as a standard classification problem, labeling each statement in isolation. However, the interpretation of monetary-policy communication is inherently relative: market reactions depend not only on the tone of a statement, but also on how that tone shifts across meetings. We introduce Delta-Consistent Scoring (DCS), an annotation-free framework that maps frozen large language model (LLM) representations to continuous stance scores by jointly modeling absolute stance and relative inter-meeting shifts. Rather than relying on manual hawkish--dovish labels, DCS uses consecutive meetings as a source of self-supervision. It learns an absolute stance score for each statement and a relative shift score between consecutive statements. A delta-consistency objective encourages changes in absolute scores to align with the relative shifts. This allows DCS to recover a temporally coherent stance trajectory without manual labels. Across four LLM backbones, DCS consistently outperforms supervised probes and LLM-as-judge baselines, achieving up to 71.1% accuracy on sentence-level hawkish--dovish classification. The resulting meeting-level scores are also economically meaningful: they correlate strongly with inflation indicators and are significantly associated with Treasury yield movements. Overall, the results suggest that LLM representations encode monetary-policy signals that can be recovered through relative temporal structure.

Grassroots currencies turn mutual trust into liquidity: a grassroots coin is a unit of its issuer's debt, backed by the issuer's goods and services, which the issuer must redeem, 1-for-1, against any coin they hold; liquidity arises from mutual credit lines, formed by the voluntary exchange of coins among persons who trust each other. As coins are redeemable 1-for-1, the exchange must be 1-for-1 as well, lest prompt redemption after it leave one party with undue profit. Thus, grassroots coins are incongruent with interest-bearing credit. Here, we extend grassroots currencies to include also grassroots bonds, units of their issuer's debt due at a later date. Upon maturity, the bearer of the bond may redeem it against a coin of the issuer, so liquid coins can be lent against interest-bearing bonds. We specify bonds by adding Date and Escrow clauses to the social contract of grassroots currencies: the contract enforces the redemption of a bond when it is mature according to the date stated by the issuer, who undertakes to keep it current. We show that the voluntary swap of coins and bonds can realise the basic financial instruments: loans, sale of debt, and forward contracts, and, with an escrow agent, loans with payment schedules, options, collateral, guarantees, insurance, credit default swaps, letters of credit, and credit lines. We extend the liquidity ratios of corporate finance to bonds, with maturity as asset class, and prove that a community clears its debts by redemptions exactly when no member owes more than they hold, and that it does so without coordination once dates advance and persons act on their rights. Grassroots currencies that include coins and bonds are implemented in GLP, a concurrent logic programming language running on Dart, as a program derived from the contract and demonstrated by a village market of six agents and an escrow agent.

We present a Temporal Rule-Anchored Chain-of-Evidence (TRACE) on knowledge graphs for interpretable stock movement prediction that unifies symbolic relational priors, dynamic graph exploration, and LLM-guided decision making in a single end-to-end pipeline. The approach performs rule-guided multi-hop exploration restricted to admissible relation sequences, grounds candidate reasoning chains in contemporaneous news, and aggregates fully grounded evidence into auditable UP/DOWN verdicts with human-readable paths connecting text and structure. On an S&P~500 benchmark, the method achieves 55.1% accuracy, 55.7% precision, 71.5% recall, and 60.8% F1, surpassing strong baselines and improving recall and F1 over the best graph baseline under identical evaluation. The gains stem from (i) rule-guided exploration that focuses search on economically meaningful motifs rather than arbitrary walks, and (ii) text-grounded consolidation that selectively aggregates high-confidence, fully grounded hypotheses instead of uniformly pooling weak signals. Together, these choices yield higher sensitivity without sacrificing selectivity, delivering predictive lift with faithful, auditably interpretable explanations.

In this paper, we propose LingDT-VL-OCR, a document parsing system tailored to financial-domain documents, transforming ultra-long financial PDFs into semantically consistent, highly accurate, structured outputs with auditing-grade provenance. To address finance-specific challenges such as complex layouts, cross-page structural discontinuities, and cell-level referencing capability, LingDT-VL-OCR combines (1) a Cross-page Contents Consolidation algorithm to restore continuity across pages and a Document-level Heading Hierarchy Reconstruction (DHR) module to build a globally consistent Table of Contents (TOC) tree for structure-aware retrieval, and (2) a difficulty-adaptive curriculum learning training strategy for table parsing, together with a CellBBoxRegressor module that uses structural anchor tokens to localize table cells from decoder hidden states without external detectors. Experiments demonstrate that our model shows high performance on the Overall metric of OmniDocBench. To enable realistic evaluation in the financial vertical, we further introduce FinDocBench, a benchmark that includes six financial document categories with expert-verified annotations and evaluation metrics including Table of Contents edit-distance-based similarity (TocEDS), cross-page concatenated TEDS, and Table Cell Intersection over Union (C-IoU). We evaluate a wide range of state-of-the-art models on FinDocBench to assess their capabilities and remaining limitations on financial documents. Overall, LingDT-VL-OCR and FinDocBench provide a practical foundation for reliable downstream financial document applications.

Existing LLM safety evaluations rely on binary attack-success rates and domain-agnostic taxonomies, leaving regulated Banking, Financial Services, and Insurance (BFSI) deployments exposed to failures elicited through legally or professionally plausible framing. We introduce RAHS (Risk-Adjusted Harm Score), a risk-sensitive metric jointly capturing disclosure severity, disclaimer mitigation, and inter-judge agreement, and FinRedTeamBench, a 989-prompt benchmark spanning seven BFSI risk areas and 34 sub-categories mapped to regulatory frameworks. Evaluation uses an ensemble of three heterogeneous LLM judges, validated against human experts, and an adaptive multi-turn red-teaming pipeline. On nine open-weight models, RAHS preserves separation under near-ceiling ASR, ranking is stable under hyperparameter sweeps, and multi-turn pressure drives not only more jailbreaks but more operationally severe disclosures, exposing failure modes that single-turn, domain-agnostic evaluations cannot reveal.

We formalize a macro-financial stress test for rapid AI adoption. Rather than a productivity bust or existential risk, we identify a distribution-and-contract mismatch: AI-generated abundance coexists with demand deficiency because economic institutions are anchored to human cognitive scarcity. Three mechanisms formalize this channel. First, a displacement spiral with competing reinstatement effects: each firm's rational decision to substitute AI for labor reduces aggregate labor income, which reduces aggregate demand, accelerating further AI adoption. We derive conditions on the AI capability growth rate, diffusion speed, and reinstatement rate under which the net feedback is self-limiting versus explosive. Second, Ghost GDP: when AI-generated output substitutes for labor-generated output, monetary velocity declines monotonically in the labor share absent compensating transfers, creating a wedge between measured output and consumption-relevant income. Third, intermediation collapse: AI agents that reduce information frictions compress intermediary margins toward pure logistics costs, triggering repricing across SaaS, payments, consulting, insurance, and financial advisory. Because top-quintile earners drive 47--65% of U.S.\ consumption and face the highest AI exposure, the transmission into private credit ($2.5 trillion globally) and mortgage markets ($13 trillion) is disproportionate. We derive eleven testable predictions with explicit falsification conditions. Calibrated simulations disciplined by FRED time series and BLS occupation-level data quantify conditions under which stable adjustment transitions to explosive crisis.

Large language models are increasingly used for financial analysis and investment research, yet systematic evaluation of their financial reasoning capabilities remains limited. In this work, we introduce the AI Financial Intelligence Benchmark (AFIB), a multi-dimensional evaluation framework designed to assess financial analysis capabilities across five dimensions: factual accuracy, analytical completeness, data recency, model consistency, and failure patterns. We evaluate five AI systems: GPT, Gemini, Perplexity, Claude, and SuperInvesting, using a dataset of 95+ structured financial analysis questions derived from real-world equity research tasks. The results reveal substantial differences in performance across models. Within this benchmark setting, SuperInvesting achieves the highest aggregate performance, with an average factual accuracy score of 8.96/10 and the highest completeness score of 56.65/70, while also demonstrating the lowest hallucination rate among evaluated systems. Retrieval-oriented systems such as Perplexity perform strongly on data recency tasks due to live information access but exhibit weaker analytical synthesis and consistency. Overall, the results highlight that financial intelligence in large language models is inherently multi-dimensional, and systems that combine structured financial data access with analytical reasoning capabilities provide the most reliable performance for complex investment research workflows.

The integration of Large Language Models (LLMs) into the financial domain is driving a paradigm shift from passive information retrieval to dynamic, agentic interaction. While general-purpose tool learning has witnessed a surge in benchmarks, the financial sector, characterized by high stakes, strict compliance, and rapid data volatility, remains critically underserved. Existing financial evaluations predominantly focus on static textual analysis or document-based QA, ignoring the complex reality of tool execution. Conversely, general tool benchmarks lack the domain-specific rigor required for finance, often relying on toy environments or a negligible number of financial APIs. To bridge this gap, we introduce FinToolBench, the first real-world, runnable benchmark dedicated to evaluating financial tool learning agents. Unlike prior works limited to a handful of mock tools, FinToolBench establishes a realistic ecosystem coupling 760 executable financial tools with 295 rigorous, tool-required queries. We propose a novel evaluation framework that goes beyond binary execution success, assessing agents on finance-critical dimensions: timeliness, intent type, and regulatory domain alignment. Furthermore, we present FATR, a finance-aware tool retrieval and reasoning baseline that enhances stability and compliance. By providing the first testbed for auditable, agentic financial execution, FinToolBench sets a new standard for trustworthy AI in finance. The tool manifest, execution environment, and evaluation code will be open-sourced to facilitate future research.

Leveraged ETFs (L-ETFs) are exchange-traded funds that achieve price movements several times greater than an index by holding index-linked futures such as Nikkei Stock Average Index futures. It is known that when the price of an L-ETF falls, the L-ETF uses the liquidity of futures to limit the decline through arbitrage trading. Conversely, when the price of a futures contract falls, the futures contract uses the liquidity of the L-ETF to limit its decline. However, the impact of arbitrage trading on the liquidity of these markets has been little studied. Therefore, the present study used artificial market simulations to investigate how the liquidity (Volume, SellDepth, BuyDepth, Tightness) of both markets changes when prices plummet in either (i.e., the L-ETF or futures market), depending on the presence or absence of arbitrage trading. As a result, it was found that when erroneous orders occur in the L-ETF market, the existence of arbitrage trading causes liquidity to be supplied from the futures market to the L-ETF market in terms of SellDepth and Tightness. When erroneous orders occur in the futures market, the existence of arbitrage trading causes liquidity to be supplied from the L-ETF market to the futures market in terms of SellDepth and Tightness, and liquidity to be supplied from the futures market to the L-ETF market in terms of Volume. We also analyzed the internal market mechanisms that led to these results.

Central Bank Digital Currency (CBDCs) are becoming a new digital financial tool aimed at financial inclusion, increased monetary stability, and improved efficiency of payment systems, as they are issued by central banks. One of the most important aspects is that the CBDC must offer secure offline payment methods to users, allowing them to retain cash-like access without violating Anti-Money Laundering and Counter-terrorism Financing (AML/CFT) rules. The offline CBDC ecosystems will provide financial inclusion, empower underserved communities, and ensure equitable access to digital payments, even in connectivity-poor remote locations. With the rapid growth of Internet of Things (IoT) devices in our everyday lives, they are capable of performing secure digital transactions. Integrating offline CBDC payment with IoT devices enables seamless, automated payment without internet connectivity. However, IoT devices face special challenges due to their resource-constrained nature. This makes it difficult to include features such as double-spending prevention, privacy preservation, low-computation operation, and digital identity management. The work proposes a privacy-preserving offline CBDC model with integrated secure elements (SEs), zero-knowledge proofs (ZKPs), and intermittent synchronisation to conduct offline payments on IoT hardware. The proposed model is based on recent improvements in offline CBDC prototypes, regulations and cryptographic design choices such as hybrid architecture that involves using combination of online and offline payment in IoT devices using secure hardware with lightweight zero-knowledge proof cryptographic algorithm.

Operational disruptions in retail payments can induce behavioral responses that outlast technical recovery and may amplify liquidity stress. We propose a multi-agent model linking card payment outages to trust dynamics, channel avoidance, and threshold-gated withdrawals. Customers and merchants interact through repeated payment attempts, while customers additionally influence one another on a Watts-Strogatz small-world network. Customers update bounded memory variables capturing accumulated negative experience (scar) and perceived systemic risk (rumor), with merchants contributing persistent broadcast signals that may lag operational recovery. We prove that, under mild conditions on memory persistence and threshold gating, aggregate withdrawal pressure can peak strictly after the outage nadir, including during the recovery phase. Simulations reproduce behavioral hysteresis and confirm delayed peaks of outflows. We further study payment substitution via instant transfer: substitution consistently reduces peak avoidance, yet its effect on cumulative outflows is non-monotonic under realistic merchant broadcast persistence. Robustness experiments across random seeds show stable qualitative behavior. The model highlights why "status green" is not equivalent to risk resolution and motivates incident response strategies that address perception, merchant messaging, and post-recovery communication in addition to technical remediation.