{"total":64,"rows":[{"id":"2503.23037","title":"Agentic Large Language Models, a survey","created":"2025-03-29","cited_by_count":108,"area":"agents"},{"id":"2510.02209","title":"StockBench: Can LLM Agents Trade Stocks Profitably In Real-world Markets?","created":"2025-10-02","cited_by_count":44,"area":"agents"},{"id":"2602.05665","title":"Graph-based Agent Memory: Taxonomy, Techniques, and Applications","created":"2026-02-05","cited_by_count":25,"area":"agents"},{"id":"2502.15865","title":"Standard Benchmarks Fail -- Auditing LLM Agents in Finance Must Prioritize Risk","created":"2025-02-21","cited_by_count":13,"area":"agents"},{"id":"2511.03628","title":"LiveTradeBench: Seeking Real-World Alpha with Large Language Models","created":"2025-11-05","cited_by_count":13,"area":"lr"},{"id":"2504.02181","title":"A Survey of Scaling in Large Language Model Reasoning","created":"2025-04-02","cited_by_count":10,"area":"lr"},{"id":"2512.13168","title":"Finch: Benchmarking Finance & Accounting across Spreadsheet-Centric Enterprise Workflows","created":"2025-12-15","cited_by_count":10,"area":null},{"id":"2503.21422","title":"From Deep Learning to LLMs: A survey of AI in Quantitative Investment","created":"2025-03-27","cited_by_count":9,"area":null},{"id":"2503.08750","title":"Exposing Product Bias in LLM Investment Recommendation","created":"2025-03-11","cited_by_count":6,"area":null},{"id":"2506.04098","title":"TextAtari: 100K Frames Game Playing with Language Agents","created":"2025-06-04","cited_by_count":6,"area":"agents"},{"id":"2605.15412","title":"From Feedback Loops to Policy Updates: Reinforcement Fine-Tuning for LLM-Based Alpha Factor Discovery","created":"2026-05-14","cited_by_count":6,"area":null},{"id":"2606.29771","title":"CLQT: A Closed-Loop, Cost-Aware, Strategy-Consistent Benchmark for Diagnostic Evaluation of LLM Portfolio-Management Agents","created":"2026-06-29","cited_by_count":6,"area":"agents"},{"id":"2509.12042","title":"FinGEAR: Financial Mapping-Guided Enhanced Answer Retrieval","created":"2025-09-15","cited_by_count":5,"area":"rag"},{"id":"2512.00417","title":"CryptoBench: A Dynamic Benchmark for Expert-Level Evaluation of LLM Agents in Cryptocurrency","created":"2025-11-29","cited_by_count":5,"area":"agents"},{"id":"2603.27771","title":"Emergent Risks in Generative Multi-Agent Systems","created":"2026-03-29","cited_by_count":5,"area":null},{"id":"2503.18313","title":"Will LLMs be Professional at Fund Investment? DeepFund: A Live Arena Perspective","created":"2025-03-24","cited_by_count":4,"area":null},{"id":"2506.13055","title":"CFBenchmark-MM: Chinese Financial Assistant Benchmark for Multimodal Large Language Model","created":"2025-06-16","cited_by_count":4,"area":"mllm"},{"id":"2602.16990","title":"Conv-FinRe: A Conversational and Longitudinal Benchmark for Utility-Grounded Financial Recommendation","created":"2026-02-19","cited_by_count":4,"area":null},{"id":"2603.23638","title":"Can LLM Agents Be CFOs? Benchmarking Long-Horizon Resource Allocation in an Uncertain Enterprise Environment","created":"2026-03-24","cited_by_count":4,"area":"agents"},{"id":"2604.10015","title":"FinTrace: Holistic Trajectory-Level Evaluation of LLM Tool Calling for Long-Horizon Financial Tasks","created":"2026-04-11","cited_by_count":4,"area":"agents"},{"id":"2605.14355","title":"Herculean: An Agentic Benchmark for Financial Intelligence","created":"2026-05-14","cited_by_count":4,"area":"agents"},{"id":"2605.00706","title":"FinSafetyBench: Evaluating LLM Safety in Real-World Financial Scenarios","created":"2026-05-01","cited_by_count":3,"area":"safety"},{"id":"2605.27887","title":"PortBench: A Correlation-Aware, Full-Pipeline Benchmark for LLM-Driven Portfolio Management","created":"2026-05-27","cited_by_count":3,"area":null},{"id":"2506.13066","title":"FinLMM-R1: Enhancing Financial Reasoning in LMM through Scalable Data and Reward Design","created":"2025-06-16","cited_by_count":2,"area":"lr"},{"id":"2506.21591","title":"FinEval-KR: A Financial Domain Evaluation Framework for Large Language Models' Knowledge and Reasoning","created":"2025-06-18","cited_by_count":2,"area":"lr"},{"id":"2507.22936","title":"Evaluating Large Language Models (LLMs) in Financial NLP: A Comparative Study on Financial Report Analysis","created":"2025-07-24","cited_by_count":2,"area":null},{"id":"2510.17491","title":"Empowering Real-World: A Survey on the Technology, Practice, and Evaluation of LLM-driven Industry Agents","created":"2025-10-20","cited_by_count":2,"area":"lr"},{"id":"2512.02261","title":"TradeTrap: Are LLM-based Trading Agents Truly Reliable and Faithful?","created":"2025-12-01","cited_by_count":2,"area":"agents"},{"id":"2603.17694","title":"MALLES: A Multi-agent LLMs-based Economic Sandbox with Consumer Preference Alignment","created":"2026-03-18","cited_by_count":2,"area":"agents"},{"id":"2606.26350","title":"OpenFinGym: A Verifiable Multi-Task Gym Environment for Evaluating Quant Agents","created":"2026-06-24","cited_by_count":2,"area":"agents"},{"id":"2507.22940","title":"Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes","created":"2025-07-25","cited_by_count":1,"area":"lr"},{"id":"2601.06088","title":"PriceSeer: Evaluating Large Language Models in Real-Time Stock Prediction","created":"2025-12-31","cited_by_count":1,"area":null},{"id":"2601.13545","title":"TruthTensor: Evaluating LLMs through Human Imitation on Prediction Market under Drift and Holistic Reasoning","created":"2026-01-20","cited_by_count":1,"area":"lr"},{"id":"2602.11304","title":"CryptoAnalystBench: Failures in Multi-Tool Long-Form LLM Analysis","created":"2026-02-11","cited_by_count":1,"area":"agents"},{"id":"2603.08704","title":"Evaluating Financial Intelligence in Large Language Models: Benchmarking SuperInvesting AI with LLM Engines","created":"2026-03-09","cited_by_count":1,"area":"lr"},{"id":"2603.16434","title":"From Natural Language to Executable Option Strategies via Large Language Models","created":"2026-03-17","cited_by_count":1,"area":null},{"id":"2603.18469","title":"GAIN: A Benchmark for Goal-Aligned Decision-Making of Large Language Models under Imperfect Norms","created":"2026-03-19","cited_by_count":1,"area":null},{"id":"2604.04220","title":"TimeSeek: Temporal Reliability of Agentic Forecasters","created":"2026-04-05","cited_by_count":1,"area":"agents"},{"id":"2605.13050","title":"Context Training with Active Information Seeking","created":"2026-05-13","cited_by_count":1,"area":null},{"id":"2605.21482","title":"DeepWeb-Bench: A Deep Research Benchmark Demanding Massive Cross-Source Evidence and Long-Horizon Derivation","created":"2026-05-20","cited_by_count":1,"area":null},{"id":"2607.24273","title":"INS-ActBench: A Comprehensive Benchmark for Assessing Professional Actuarial Capability of Large Language Models","created":"2026-07-27","cited_by_count":1,"area":null},{"id":"2608.01204","title":"ShiJianBench: From Dialogue to Decision for Long-Horizon Evaluation of Investment Advisors","created":"2026-08-02","cited_by_count":1,"area":null},{"id":"2608.23058","title":"LLM-based Agents for Forecasting and Prediction: Methods, Training, Evaluation, and Applications","created":"2026-08-24","cited_by_count":1,"area":"agents"},{"id":"2609.04667","title":"ERPBench: Evaluating LLM Agents for Enterprise Decision-Making Across Competitive Market Ecologies","created":"2026-09-04","cited_by_count":1,"area":"agents"},{"id":"2512.02230","title":"Benchmarking LLM Agents for Wealth-Management Workflows","created":"2025-12-01","cited_by_count":0,"area":"agents"},{"id":"2604.26235","title":"LATTICE: Evaluating Decision Support Utility of Crypto Agents","created":"2026-04-29","cited_by_count":0,"area":"agents"},{"id":"2605.01451","title":"Auditing demographic bias in AI-based emergency police dispatch: a cross-lingual evaluation of eleven large language models","created":"2026-05-02","cited_by_count":0,"area":null},{"id":"2606.04978","title":"Probing Outcome-Level Resemblance and Mechanism-Level Alignment in LLM Risk Decisions: Evidence from the St. Petersburg Game","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2606.08285","title":"Beyond Agent Architecture: Execution Assumptions and Reproducibility in LLM-Based Trading Systems","created":"2026-06-06","cited_by_count":0,"area":"agents"},{"id":"2607.11141","title":"NextFund: A Unified Performance Tracking Platform for Agentic Portfolio Management","created":"2026-07-13","cited_by_count":0,"area":"agents"},{"id":"2607.16057","title":"Frontier AI performance across the business disciplines: a case-grounded benchmark of knowledge work and analytical reasoning","created":"2026-07-17","cited_by_count":0,"area":"lr"},{"id":"2607.21340","title":"Capital Markets LLM Reliability Score (CM-LRS): From Plausible to Bankable","created":"2026-07-23","cited_by_count":0,"area":null},{"id":"2607.25297","title":"Hybrid Analysis for Secure MCP Tool Use in LLM Agents","created":"2026-07-28","cited_by_count":0,"area":"agents"},{"id":"2608.09988","title":"OpenPM: Auditable Point-in-Time Evaluation for LLM Portfolio-Management Agents","created":"2026-08-06","cited_by_count":0,"area":"agents"},{"id":"2608.11232","title":"Backtrader-Bench: Benchmarking LLM Agents on Algorithmic Trading with Self-Generated MCQs","created":"2026-07-31","cited_by_count":0,"area":"agents"},{"id":"2609.00731","title":"Agentic Empirical Asset Pricing: Methodological Foundations","created":"2026-09-01","cited_by_count":0,"area":"agents"},{"id":"2609.19705","title":"SoK: Trading Agents or Market Crashers? Dissecting Robustness and Security Failures in Academic Financial LLM Trading Schemes","created":"2026-09-17","cited_by_count":0,"area":"agents"},{"id":"2609.30705","title":"The Price of Thought: Does Test-Time Reasoning Pay in LLM Trading?","created":"2026-09-25","cited_by_count":0,"area":"lr"},{"id":"2609.34510","title":"Can AI Make Money in Crypto? Measuring the Gap from Backtests to Real Markets","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.35559","title":"From Search to Research: Exploring Search Scaling in Autonomous Quantitative Factor Mining","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2610.00710","title":"ReLiveGym: Evaluating Long-Lived Agents over Weeks of Replayed Reality","created":"2026-09-30","cited_by_count":0,"area":"agents"},{"id":"2610.01871","title":"Walking the Embedding Space: Datastore Extraction from Multimodal RAG","created":"2026-10-01","cited_by_count":0,"area":"mllm"},{"id":"2610.06748","title":"BazaarBench: Delegation Safety in Decentralized C2C Marketplaces Run by LLM Agents","created":"2026-10-05","cited_by_count":0,"area":"agents"},{"id":"2610.09872","title":"LiveMACE: Process-Aware Evaluation of LLM Agent Capabilities in Evolving Markets","created":"2026-10-07","cited_by_count":0,"area":"agents"}],"next_cursor":null}