{"list":"other","total":58,"rows":[{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"2310.06770","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","created":"2023-10-10","cited_by_count":3373},{"id":"2311.12022","title":"GPQA: A Graduate-Level Google-Proof Q&A Benchmark","created":"2023-11-20","cited_by_count":2879},{"id":"2307.13854","title":"WebArena: A Realistic Web Environment for Building Autonomous Agents","created":"2023-07-25","cited_by_count":2006},{"id":"2311.07911","title":"Instruction-Following Evaluation for Large Language Models","created":"2023-11-14","cited_by_count":1228},{"id":"2404.07972","title":"OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments","created":"2024-04-11","cited_by_count":1195},{"id":"2403.04132","title":"Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference","created":"2024-03-07","cited_by_count":1184},{"id":"2507.20534","title":"Kimi K2: Open Agentic Intelligence","created":"2025-07-28","cited_by_count":567},{"id":"2109.00122","title":"FinQA: A Dataset of Numerical Reasoning over Financial Data","created":"2021-09-01","cited_by_count":562},{"id":"2501.14249","title":"Humanity's Last Exam","created":"2025-01-24","cited_by_count":491},{"id":"2401.13919","title":"WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models","created":"2024-01-25","cited_by_count":438},{"id":"2310.11667","title":"SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents","created":"2023-10-18","cited_by_count":367},{"id":"2207.13332","title":"RealTime QA: What's the Answer Right Now?","created":"2022-07-27","cited_by_count":244},{"id":"2507.02833","title":"Generalizing Verifiable Instruction Following","created":"2025-07-03","cited_by_count":194},{"id":"2412.20138","title":"TradingAgents: Multi-Agents LLM Financial Trading Framework","created":"2024-12-28","cited_by_count":188},{"id":"2311.13743","title":"FinMem: A Performance-Enhanced LLM Trading Agent with Layered Memory and Character Design","created":"2023-11-23","cited_by_count":164},{"id":"2407.01476","title":"Tree Search for Language Model Agents","created":"2024-07-01","cited_by_count":151},{"id":"2402.18485","title":"A Multimodal Foundation Agent for Financial Trading: Tool-Augmented, Diversified, and Generalist","created":"2024-02-28","cited_by_count":137},{"id":"2211.00083","title":"WHEN FLUE MEETS FLANG: Benchmarks and Large Pre-trained Language Model for Financial Domain","created":"2022-10-31","cited_by_count":117},{"id":"2310.20410","title":"FollowBench: A Multi-level Fine-grained Constraints Following Benchmark for Large Language Models","created":"2023-10-31","cited_by_count":117},{"id":"2407.06567","title":"FinCon: A Synthesized LLM Multi-Agent System with Conceptual Verbal Reinforcement for Enhanced Financial Decision Making","created":"2024-07-09","cited_by_count":113},{"id":"2312.10003","title":"ReST meets ReAct: Self-Improvement for Multi-Step Reasoning LLM Agent","created":"2023-12-15","cited_by_count":81},{"id":"2508.00828","title":"Finance Agent Benchmark: Benchmarking LLMs on Real-world Financial Research Tasks","created":"2025-05-20","cited_by_count":65},{"id":"2412.18174","title":"INVESTORBENCH: A Benchmark for Financial Decision-Making Tasks with LLM-based Agent","created":"2024-12-24","cited_by_count":64},{"id":"2002.05780","title":"Reinforcement-Learning based Portfolio Management with Augmented Asset Movement Prediction States","created":"2020-02-09","cited_by_count":55},{"id":"2308.09975","title":"FinEval: A Chinese Financial Domain Knowledge Evaluation Benchmark for Large Language Models","created":"2023-08-19","cited_by_count":52},{"id":"2510.02209","title":"StockBench: Can LLM Agents Trade Stocks Profitably In Real-world Markets?","created":"2025-10-02","cited_by_count":44},{"id":"2502.16789","title":"AlphaAgent: LLM-Driven Alpha Mining with Regularized Exploration to Counteract Alpha Decay","created":"2025-02-24","cited_by_count":42},{"id":"2402.03659","title":"Learning to Generate Explainable Stock Predictions using Self-Reflective Large Language Models","created":"2024-02-06","cited_by_count":36},{"id":"2407.18957","title":"When AI Meets Finance (StockAgent): Large Language Model-based Stock Trading in Simulated Real-world Environments","created":"2024-07-15","cited_by_count":26},{"id":"2409.06289","title":"Automate Strategy Finding with LLM in Quant Investment","created":"2024-09-10","cited_by_count":26},{"id":"2406.19966","title":"Simulating Financial Market via Large Language Model based Agents","created":"2024-06-28","cited_by_count":25},{"id":"2109.13851","title":"Reinforcement Learning for Quantitative Trading","created":"2021-09-28","cited_by_count":24},{"id":"2101.07107","title":"Deep Reinforcement Learning for Active High Frequency Trading","created":"2021-01-18","cited_by_count":21},{"id":"2505.11065","title":"Time Travel is Cheating: Going Live with DeepFund for Real-Time Fund Investment Benchmarking","created":"2025-05-16","cited_by_count":21},{"id":"2505.07078","title":"Can LLM-based Financial Investing Strategies Outperform the Market in Long Run?","created":"2025-05-11","cited_by_count":20},{"id":"2510.07920","title":"Profit Mirage: Revisiting Information Leakage in LLM-based Financial Agents","created":"2025-10-09","cited_by_count":14},{"id":"2502.17967","title":"Agent Trading Arena: A Study on Numerical Understanding in LLM-Based Agents","created":"2025-02-25","cited_by_count":9},{"id":"2508.17580","title":"UQ: Assessing Language Models on Unsolved Questions","created":"2025-08-25","cited_by_count":9},{"id":"2507.09255","title":"StockSim: A Dual-Mode Order-Level Simulator for Evaluating Multi-Agent LLMs in Financial Markets","created":"2025-07-12","cited_by_count":8},{"id":"2508.00554","title":"ContestTrade: A Multi-Agent Trading System Based on Internal Contest Mechanism","created":"2025-08-01","cited_by_count":8},{"id":"2508.17565","title":"TradingGroup: A Multi-Agent Trading System with Self-Reflection and Data-Synthesis","created":"2025-08-25","cited_by_count":8},{"id":"2301.10724","title":"Select and Trade: Towards Unified Pair Trading with Hierarchical Reinforcement Learning","created":"2023-01-25","cited_by_count":6},{"id":"2402.16609","title":"Combining Transformer based Deep Reinforcement Learning with Black-Litterman Model for Portfolio Optimization","created":"2024-02-23","cited_by_count":6},{"id":"2503.18313","title":"Will LLMs be Professional at Fund Investment? DeepFund: A Live Arena Perspective","created":"2025-03-24","cited_by_count":4},{"id":"2508.02292","title":"FinWorld: An All-in-One Open-Source Platform for End-to-End Financial AI Research and Deployment","created":"2025-08-04","cited_by_count":4},{"id":"2304.00364","title":"Mastering Pair Trading with Risk-Aware Recurrent Reinforcement Learning","created":"2023-04-01","cited_by_count":3},{"id":"2505.06408","title":"A New DAPO Algorithm for Stock Trading","created":"2025-05-09","cited_by_count":2},{"id":"2507.08584","title":"To Trade or Not to Trade: An Agentic Approach to Estimating Market Risk Improves Trading Decisions","created":"2025-07-11","cited_by_count":2},{"id":"2410.20550","title":"Deep Reinforcement Learning Agents for Strategic Production Policies in Microeconomic Market Simulations","created":"2024-10-27","cited_by_count":1},{"id":"2505.14727","title":"The Evolution of Alpha in Finance Harnessing Human Insight and LLM Agents","created":"2025-05-20","cited_by_count":1}],"next_cursor":null}