{"total":100,"rows":[{"id":"2509.02547","title":"The Landscape of Agentic Reinforcement Learning for LLMs: A Survey","created":"2025-09-02","cited_by_count":205,"area":"agents"},{"id":"2509.08827","title":"A Survey of Reinforcement Learning for Large Reasoning Models","created":"2025-09-10","cited_by_count":180,"area":"lr"},{"id":"2507.21046","title":"A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence","created":"2025-07-28","cited_by_count":170,"area":"agents"},{"id":"2510.24684","title":"SPICE: Self-Play In Corpus Environments Improves Reasoning","created":"2025-10-28","cited_by_count":83,"area":null},{"id":"2511.16043","title":"Agent0: Unleashing Self-Evolving Agents from Zero Data via Tool-Integrated Reasoning","created":"2025-11-20","cited_by_count":75,"area":"lr"},{"id":"2509.07980","title":"Parallel-R1: Towards Parallel Thinking via Reinforcement Learning","created":"2025-09-09","cited_by_count":61,"area":"lr"},{"id":"2510.23595","title":"Multi-Agent Evolve: LLM Self-Improve through Co-evolution","created":"2025-10-27","cited_by_count":60,"area":"lr"},{"id":"2511.07317","title":"RLVE: Scaling Up Reinforcement Learning for Language Models with Adaptive Verifiable Environments","created":"2025-11-10","cited_by_count":50,"area":null},{"id":"2508.04652","title":"LLM Collaboration With Multi-Agent Reinforcement Learning","created":"2025-08-06","cited_by_count":49,"area":"agents"},{"id":"2601.07055","title":"Dr. Zero: Self-Evolving Search Agents without Training Data","created":"2026-01-11","cited_by_count":44,"area":"agents"},{"id":"2509.07414","title":"Language Self-Play For Data-Free Training","created":"2025-09-09","cited_by_count":43,"area":"synth"},{"id":"2509.25541","title":"Vision-Zero: Scalable VLM Self-Improvement via Strategic Gamified Self-Play","created":"2025-09-29","cited_by_count":37,"area":"mllm"},{"id":"2509.16679","title":"Reinforcement Learning Meets Large Language Models: A Survey of Advancements and Applications Across the LLM Lifecycle","created":"2025-09-20","cited_by_count":35,"area":null},{"id":"2602.21320","title":"Tool-R0: Self-Evolving LLM Agents for Tool-Learning from Zero Data","created":"2026-02-24","cited_by_count":34,"area":"agents"},{"id":"2605.26684","title":"Beyond Trajectory-Level Attribution: Graph-Based Credit Assignment for Agentic Reinforcement Learning","created":"2026-05-26","cited_by_count":31,"area":"agents"},{"id":"2509.23863","title":"SPELL: Self-Play Reinforcement Learning for Evolving Long-Context Language Models","created":"2025-09-28","cited_by_count":29,"area":"lr"},{"id":"2510.11062","title":"Stronger-MAS: Multi-Agent Reinforcement Learning for Collaborative LLMs","created":"2025-10-13","cited_by_count":28,"area":"lr"},{"id":"2510.00553","title":"On Predictability of Reinforcement Learning Dynamics for Large Language Models","created":"2025-10-01","cited_by_count":23,"area":"lr"},{"id":"2510.01051","title":"GEM: A Gym for Agentic LLMs","created":"2025-10-01","cited_by_count":23,"area":"agents"},{"id":"2512.15699","title":"FrontierCS: Evolving Challenges for Evolving Intelligence","created":"2025-12-17","cited_by_count":23,"area":null},{"id":"2510.25779","title":"Magentic Marketplace: An Open-Source Environment for Studying Agentic Markets","created":"2025-10-27","cited_by_count":19,"area":"agents"},{"id":"2604.27660","title":"From Context to Skills: Can Language Models Learn from Context Skillfully?","created":"2026-04-30","cited_by_count":19,"area":null},{"id":"2604.01985","title":"World Action Verifier: Self-Improving World Models via Forward-Inverse Asymmetry","created":"2026-04-02","cited_by_count":18,"area":"wm"},{"id":"2608.06296","title":"On-Policy Self-Distillation without Any Supervision","created":"2026-08-06","cited_by_count":17,"area":"lr"},{"id":"2510.15414","title":"MARSHAL: Incentivizing Multi-Agent Reasoning via Self-Play with Strategic LLMs","created":"2025-10-17","cited_by_count":16,"area":"lr"},{"id":"2602.00359","title":"Position: Agentic Evolution is the Path to Evolving LLMs","created":"2026-01-30","cited_by_count":16,"area":"agents"},{"id":"2602.08847","title":"Dr. MAS: Stable Reinforcement Learning for Multi-Agent LLM Systems","created":"2026-02-09","cited_by_count":16,"area":"lr"},{"id":"2608.19197","title":"SPADE: Self-Play in Adaptive Synthetic Executable Environments","created":"2026-08-19","cited_by_count":12,"area":"synth"},{"id":"2601.10094","title":"V-Zero: Self-Improving Multimodal Reasoning with Zero Annotation","created":"2026-01-15","cited_by_count":10,"area":"lr"},{"id":"2602.13103","title":"R-Diverse: Mitigating Diversity Illusion in Self-Play LLM Training","created":"2026-02-13","cited_by_count":10,"area":"lr"},{"id":"2607.22529","title":"Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills","created":"2026-07-24","cited_by_count":10,"area":"synth"},{"id":"2606.07412","title":"Socratic-SWE: Self-Evolving Coding Agents via Trace-Derived Agent Skills","created":"2026-06-05","cited_by_count":9,"area":"agents"},{"id":"2507.08892","title":"Multi-Actor Generative Artificial Intelligence as a Game Engine","created":"2025-07-10","cited_by_count":8,"area":null},{"id":"2510.27072","title":"Towards Understanding Self-play for LLM Reasoning","created":"2025-10-31","cited_by_count":8,"area":"lr"},{"id":"2601.04809","title":"SCALER:Synthetic Scalable Adaptive Learning Environment for Reasoning","created":"2026-01-08","cited_by_count":8,"area":"lr"},{"id":"2601.05167","title":"RelayLLM: Efficient Reasoning via Collaborative Decoding","created":"2026-01-08","cited_by_count":8,"area":"lr"},{"id":"2601.21972","title":"Learning Decentralized LLM Collaboration with Multi-Agent Actor Critic","created":"2026-01-29","cited_by_count":8,"area":"agents"},{"id":"2606.12191","title":"Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application","created":"2026-06-10","cited_by_count":8,"area":"agents"},{"id":"2511.00602","title":"OpenSIR: Open-Ended Self-Improving Reasoner","created":"2025-11-01","cited_by_count":7,"area":"lr"},{"id":"2601.03335","title":"Digital Red Queen: Adversarial Program Evolution in Core War with LLMs","created":"2026-01-06","cited_by_count":7,"area":null},{"id":"2602.03109","title":"One Model, All Roles: Multi-Turn, Multi-Agent Self-Play Reinforcement Learning for Conversational Social Intelligence","created":"2026-02-03","cited_by_count":7,"area":null},{"id":"2604.09855","title":"Instructing LLMs to Negotiate using Reinforcement Learning with Verifiable Rewards","created":"2026-04-10","cited_by_count":7,"area":null},{"id":"2604.14054","title":"$\\pi$-Play: Multi-Agent Self-Play via Privileged Self-Distillation without External Data","created":"2026-04-15","cited_by_count":7,"area":"distill"},{"id":"2512.16917","title":"Generative Adversarial Reasoner: Enhancing LLM Reasoning with Adversarial Reinforcement Learning","created":"2025-12-18","cited_by_count":6,"area":"lr"},{"id":"2601.10567","title":"Generative AI collective behavior needs an interactionist paradigm","created":"2026-01-15","cited_by_count":6,"area":null},{"id":"2602.10356","title":"Autonomous Continual Learning for Environment Adaptation of Computer-Use Agents","created":"2026-02-10","cited_by_count":6,"area":"agents"},{"id":"2603.15255","title":"SAGE: Multi-Agent Self-Evolution for LLM Reasoning","created":"2026-03-16","cited_by_count":6,"area":"lr"},{"id":"2608.12253","title":"One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL","created":"2026-08-12","cited_by_count":6,"area":"agents"},{"id":"2603.01221","title":"Epistemic Gain, Aleatoric Cost: Uncertainty Decomposition in Multi-Agent Debate for Math Reasoning","created":"2026-03-01","cited_by_count":5,"area":"lr"},{"id":"2603.09022","title":"MEMO: Memory-Augmented Model Context Optimization for Robust Multi-Turn Multi-Agent LLM Games","created":"2026-03-09","cited_by_count":5,"area":"agents"},{"id":"2608.31075","title":"Scaling Large Reasoning Models beyond Human Supervision: A Path toward Superintelligence","created":"2026-08-31","cited_by_count":5,"area":"lr"},{"id":"2609.05295","title":"RISE: Recursive Improvement via Self-Extrapolating Policy Distillation","created":"2026-09-04","cited_by_count":5,"area":"distill"},{"id":"2604.11805","title":"Solving Physics Olympiad via Reinforcement Learning on Physics Simulators","created":"2026-04-13","cited_by_count":4,"area":"lr"},{"id":"2605.04984","title":"Self-Induced Outcome Potential: Turn-Level Credit Assignment for Agents without Verifiers","created":"2026-05-06","cited_by_count":4,"area":"lr"},{"id":"2606.12683","title":"From AGI to ASI","created":"2026-06-10","cited_by_count":4,"area":null},{"id":"2608.17776","title":"Debate Training Reduces Reward Hacking in RLAIF","created":"2026-08-18","cited_by_count":4,"area":"alignment"},{"id":"2509.23166","title":"Test-Time Policy Adaptation for Enhanced Multi-Turn Interactions with LLMs","created":"2025-09-27","cited_by_count":3,"area":null},{"id":"2601.15047","title":"Game-Theoretic Lens on LLM-based Multi-Agent Systems","created":"2026-01-21","cited_by_count":3,"area":"lr"},{"id":"2601.20829","title":"Training Reasoning Models on Saturated Problems via Failure-Prefix Conditioning","created":"2026-01-28","cited_by_count":3,"area":"lr"},{"id":"2607.20166","title":"Audio-Zero: Label-Free Self-Evolution for Fine-Grained Audio Reasoning","created":"2026-07-22","cited_by_count":3,"area":"lr"},{"id":"2607.25308","title":"CAST: Game Solvers as Turn-Level Teachers for LLM Agents","created":"2026-07-28","cited_by_count":3,"area":"agents"},{"id":"2510.08872","title":"GTAlign: Game-Theoretic Alignment of LLM Assistants for Social Welfare","created":"2025-10-10","cited_by_count":2,"area":null},{"id":"2602.23668","title":"PseudoAct: Leveraging Pseudocode Synthesis for Flexible Planning and Action Control in Large Language Model Agents","created":"2026-02-27","cited_by_count":2,"area":"agents"},{"id":"2605.08327","title":"Interactive Critique-Revision Training for Reliable Structured LLM Generation","created":"2026-05-08","cited_by_count":2,"area":"lr"},{"id":"2605.10038","title":"TimeClaw: A Time-Series AI Agent with Exploratory Execution Learning","created":"2026-05-11","cited_by_count":2,"area":"agents"},{"id":"2606.04507","title":"Self-Evolving Deep Research via Joint Generation and Evaluation","created":"2026-06-03","cited_by_count":2,"area":"synth"},{"id":"2606.07812","title":"Scaling Participation in Modular AI Systems","created":"2026-06-05","cited_by_count":2,"area":null},{"id":"2606.08656","title":"From Player to Master: Enhancing Test-Time Learning of LLM Agents via Reinforcement Learning over Memory","created":"2026-06-07","cited_by_count":2,"area":"agents"},{"id":"2606.17657","title":"Using Cognitive Models to Improve Language Model Simulation of Human Persuasion Games","created":"2026-06-16","cited_by_count":2,"area":null},{"id":"2608.09128","title":"Social Gym and SPaRTan: Benchmarking and Improving LLM Social Reasoning via Multi-Agent Game Tournaments","created":"2026-08-10","cited_by_count":2,"area":"lr"},{"id":"2512.17043","title":"UniRel: Relation-Centric Knowledge Graph Question Answering with RL-Tuned LLM Reasoning","created":"2025-12-18","cited_by_count":1,"area":"lr"},{"id":"2601.21754","title":"Language-based Trial and Error Falls Behind in the Era of Experience","created":"2026-01-29","cited_by_count":1,"area":"agents"},{"id":"2601.22297","title":"Learning from Self-Debate: Preparing Reasoning Models for Multi-Agent Debate","created":"2026-01-29","cited_by_count":1,"area":"lr"},{"id":"2602.16488","title":"Learning to Learn from Language Feedback with Social Meta-Learning","created":"2026-02-18","cited_by_count":1,"area":null},{"id":"2607.23802","title":"From RLVR to RLSVR: Task Transformation Induces Self-Verifiable Rewards for Open-Ended LLM Self-Improvement","created":"2026-07-26","cited_by_count":1,"area":"lr"},{"id":"2609.39102","title":"False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents","created":"2026-09-30","cited_by_count":1,"area":null},{"id":"2610.08327","title":"MedZERO: Self-Evolving Agents for Open-Ended Medical Reasoning Through Controlled Knowledge Accumulation","created":"2026-10-06","cited_by_count":1,"area":"lr"},{"id":"2603.23964","title":"From Pixels to Digital Agents: An Empirical Study on the Taxonomy and Technological Trends of Reinforcement Learning Environments","created":"2026-03-25","cited_by_count":0,"area":"lr"},{"id":"2604.17696","title":"Stratagem: Learning Transferable Reasoning via Trajectory-Modulated Game Self-Play","created":"2026-04-20","cited_by_count":0,"area":"lr"},{"id":"2605.04906","title":"Strat-Reasoner: Reinforcing Strategic Reasoning of LLMs in Multi-Agent Games","created":"2026-05-06","cited_by_count":0,"area":"lr"},{"id":"2605.11666","title":"Evolutionary Task Discovery: Advancing Reasoning Frontiers via Skill Composition and Complexity Scaling","created":"2026-05-12","cited_by_count":0,"area":"lr"},{"id":"2606.09052","title":"INFUSER: Influence-Guided Self-Evolution Improves Reasoning","created":"2026-06-08","cited_by_count":0,"area":"lr"},{"id":"2606.22495","title":"Grounded Scaling: Why Agentic AI Needs Deterministic Environments","created":"2026-06-21","cited_by_count":0,"area":"agents"},{"id":"2607.06935","title":"Mathematical methods of reinforcement learning","created":"2026-07-08","cited_by_count":0,"area":"deeprl"},{"id":"2608.06933","title":"Ask-E: An Environment for Calibrated Question Generation","created":"2026-08-07","cited_by_count":0,"area":null},{"id":"2608.11746","title":"Epiplexity Guided Data Selection and Generation for Out-of-Distribution Generalization","created":"2026-08-12","cited_by_count":0,"area":null},{"id":"2608.21871","title":"The Chase Is the Curriculum, the Capture Anchors the Credit: Pursuit-Evasion Self-Play for Zero-Data LLM Reasoning","created":"2026-08-22","cited_by_count":0,"area":"lr"},{"id":"2608.23969","title":"Investigating Knowledge Transfer Across Interactive Dialogue Games","created":"2026-08-25","cited_by_count":0,"area":null},{"id":"2609.32208","title":"Witness: Discovery, Deciphering, and Epiphany in Interactive Puzzle Environments","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.32749","title":"Retrospective Distillation Attribution via Normalized Response Similarity","created":"2026-09-26","cited_by_count":0,"area":"lr"},{"id":"2609.39076","title":"Multi-LLM Collaborative Alignment via Stackelberg Games","created":"2026-09-30","cited_by_count":0,"area":"alignment"},{"id":"2610.04299","title":"Questioning the Questions: Sustaining Self-Evolution in Reasoning Models","created":"2026-10-03","cited_by_count":0,"area":"lr"},{"id":"2610.04441","title":"LocusRL: Diagnosing LLM Reward and Policy Interventions in Competitive Games","created":"2026-10-03","cited_by_count":0,"area":null},{"id":"2610.06204","title":"Do Small Language Models Learn to Negotiate? A Controlled Scaling Study of RL-Trained Sellers","created":"2026-10-05","cited_by_count":0,"area":"agents"},{"id":"2610.09856","title":"Self-Evolve With a Reference:Anchored Training of Tool-Integrated Agents","created":"2026-10-07","cited_by_count":0,"area":"agents"},{"id":"2610.13995","title":"GameSmith: Scaling Zero-Sum Self-Play with Synthesised Games","created":"2026-09-26","cited_by_count":0,"area":"synth"},{"id":"2610.14163","title":"AutoEnvScaling: Automating the Data Flywheel with Terminal Agents","created":"2026-10-09","cited_by_count":0,"area":"agents"},{"id":"2610.15888","title":"Variance-Optimal State Resampling for Reinforcement Learning with Verifiable Rewards","created":"2026-10-11","cited_by_count":0,"area":"lr"},{"id":"2610.17456","title":"Compositional RL: Evaluating and Training LLMs for Collaborative Reasoning","created":"2026-10-12","cited_by_count":0,"area":"lr"},{"id":"2610.17893","title":"Training LLMs for Multi-Agent Collaboration with Verifiable Information Rewards","created":"2026-10-13","cited_by_count":0,"area":"agents"}],"next_cursor":null}