{"list":"other","total":58,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"id":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"2409.19256","title":"HybridFlow: A Flexible and Efficient RLHF Framework","created":"2024-09-28","cited_by_count":2057},{"id":"2308.08155","title":"AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation","created":"2023-08-16","cited_by_count":1988},{"id":"2308.00352","title":"MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework","created":"2023-08-01","cited_by_count":1808},{"id":"2409.12186","title":"Qwen2.5-Coder Technical Report","created":"2024-09-18","cited_by_count":1203},{"id":"2307.07924","title":"ChatDev: Communicative Agents for Software Development","created":"2023-07-16","cited_by_count":919},{"id":"1712.01815","title":"Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm","created":"2017-12-05","cited_by_count":734},{"id":"2401.01335","title":"Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models","created":"2024-01-02","cited_by_count":557},{"id":"2410.10762","title":"AFlow: Automating Agentic Workflow Generation","created":"2024-10-14","cited_by_count":432},{"id":"2310.11667","title":"SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents","created":"2023-10-18","cited_by_count":367},{"id":"2505.03335","title":"Absolute Zero: Reinforced Self-play Reasoning with Zero Data","created":"2025-05-06","cited_by_count":344},{"id":"2506.14245","title":"Reinforcement Learning with Verifiable Rewards Implicitly Incentivizes Correct Reasoning in Base LLMs","created":"2025-06-17","cited_by_count":289},{"id":"2507.02259","title":"MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent","created":"2025-07-03","cited_by_count":246},{"id":"2309.04658","title":"Exploring Large Language Models for Communication Games: An Empirical Study on Werewolf","created":"2023-09-09","cited_by_count":241},{"id":"2401.08967","title":"ReFT: Reasoning with Reinforced Fine-Tuning","created":"2024-01-17","cited_by_count":239},{"id":"2504.14225","title":"Know Me, Respond to Me: Benchmarking LLMs for Dynamic User Profiling and Personalized Responses at Scale","created":"2025-04-19","cited_by_count":178},{"id":"2310.18940","title":"Language Agents with Reinforcement Learning for Strategic Play in the Werewolf Game","created":"2023-10-29","cited_by_count":152},{"id":"2503.15478","title":"SWEET-RL: Training Multi-Turn LLM Agents on Collaborative Reasoning Tasks","created":"2025-03-19","cited_by_count":118},{"id":"2502.04644","title":"Agentic Reasoning: A Streamlined Framework for Enhancing LLM Reasoning with Agentic Tools","created":"2025-02-07","cited_by_count":106},{"id":"2506.24119","title":"SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning","created":"2025-06-30","cited_by_count":100},{"id":"2404.01230","title":"LLM as a Mastermind: A Survey of Strategic Reasoning with Large Language Models","created":"2024-04-01","cited_by_count":99},{"id":"2504.02234","title":"LLM Social Simulations Are a Promising Research Method","created":"2025-04-03","cited_by_count":99},{"id":"2403.08715","title":"SOTOPIA-$\\pi$: Interactive Learning of Socially Intelligent Language Agents","created":"2024-03-13","cited_by_count":93},{"id":"2512.06688","title":"PersonaMem-v2: Towards Personalized Intelligence via Learning Implicit User Personas and Agentic Memory","created":"2025-12-07","cited_by_count":88},{"id":"2310.03051","title":"How FaR Are Large Language Models From Agents with Theory-of-Mind?","created":"2023-10-04","cited_by_count":76},{"id":"2511.16043","title":"Agent0: Unleashing Self-Evolving Agents from Zero Data via Tool-Integrated Reasoning","created":"2025-11-20","cited_by_count":75},{"id":"2406.11050","title":"A Peek into Token Bias: Large Language Models Are Not Yet Genuine Reasoners","created":"2024-06-16","cited_by_count":73},{"id":"2510.04206","title":"AgentRL: Scaling Agentic Reinforcement Learning with a Multi-Turn, Multi-Task Framework","created":"2025-10-05","cited_by_count":62},{"id":"2510.23595","title":"Multi-Agent Evolve: LLM Self-Improve through Co-evolution","created":"2025-10-27","cited_by_count":60},{"id":"2410.13648","title":"SimpleToM: Exposing the Gap between Explicit ToM Inference and Implicit ToM Application in LLMs","created":"2024-10-17","cited_by_count":57},{"id":"2402.12071","title":"EmoBench: Evaluating the Emotional Intelligence of Large Language Models","created":"2024-02-19","cited_by_count":53},{"id":"2502.02508","title":"Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search","created":"2025-02-04","cited_by_count":53},{"id":"2407.13943","title":"Werewolf Arena: A Case Study in LLM Evaluation via Social Deduction","created":"2024-07-18","cited_by_count":45},{"id":"2410.19346","title":"AgentSense: Benchmarking Social Intelligence of Language Agents through Interactive Scenarios","created":"2024-10-25","cited_by_count":40},{"id":"2512.03627","title":"MemVerse: Multimodal Memory for Lifelong Learning Agents","created":"2025-12-03","cited_by_count":35},{"id":"2502.04424","title":"EmoBench-M: Benchmarking Emotional Intelligence for Multimodal Large Language Models","created":"2025-02-06","cited_by_count":32},{"id":"2511.19900","title":"Agent0-VL: Exploring Self-Evolving Agent for Tool-Integrated Vision-Language Reasoning","created":"2025-11-25","cited_by_count":31},{"id":"2509.23863","title":"SPELL: Self-Play Reinforcement Learning for Evolving Long-Context Language Models","created":"2025-09-28","cited_by_count":29},{"id":"2503.13415","title":"A Comprehensive Survey on Multi-Agent Cooperative Decision-Making: Scenarios, Approaches, Challenges and Perspectives","created":"2025-03-17","cited_by_count":27},{"id":"2503.12349","title":"SPIN-Bench: How Well Do LLMs Plan Strategically and Reason Socially?","created":"2025-03-16","cited_by_count":24},{"id":"2510.15414","title":"MARSHAL: Incentivizing Multi-Agent Reasoning via Self-Play with Strategic LLMs","created":"2025-10-17","cited_by_count":16},{"id":"2512.09187","title":"WOLF: Werewolf-based Observations for LLM Deception and Falsehoods","created":"2025-12-09","cited_by_count":13},{"id":"2506.00900","title":"SocialEval: Evaluating Social Intelligence of Large Language Models","created":"2025-06-01","cited_by_count":12},{"id":"2410.06195","title":"EgoSocialArena: Benchmarking the Social Intelligence of Large Language Models from a First-person Perspective","created":"2024-10-08","cited_by_count":10},{"id":"2501.14225","title":"Multi-agent KTO: Reinforcing Strategic Interactions of Large Language Model in Language Game","created":"2025-01-24","cited_by_count":10},{"id":"2504.16122","title":"SOTOPIA-S4: a user-friendly system for flexible, customizable, and large-scale social simulation","created":"2025-04-19","cited_by_count":10},{"id":"2510.14253","title":"Towards Agentic Self-Learning LLMs in Search Environment","created":"2025-10-16","cited_by_count":8},{"id":"2511.11881","title":"Better LLM Reasoning via Dual-Play","created":"2025-11-14","cited_by_count":8},{"id":"2510.23182","title":"SI-Bench: Benchmarking Social Intelligence of Large Language Models in Human-to-Human Conversations","created":"2025-10-27","cited_by_count":7},{"id":"2504.17200","title":"A RAG-Based Multi-Agent LLM System for Natural Hazard Resilience and Adaptation","created":"2025-04-24","cited_by_count":5},{"id":"2511.07922","title":"SERL: Self-Examining Reinforcement Learning on Open-Domain","created":"2025-11-11","cited_by_count":5},{"id":"2410.18906","title":"PRISM: A Methodology for Auditing Biases in Large Language Models","created":"2024-10-24","cited_by_count":4},{"id":"2506.13065","title":"MotiveBench: How Far Are We From Human-Like Motivational Reasoning in Large Language Models?","created":"2025-06-16","cited_by_count":4}],"next_cursor":null}