{"total":83,"rows":[{"id":"2505.03335","title":"Absolute Zero: Reinforced Self-play Reasoning with Zero Data","created":"2025-05-06","cited_by_count":344,"area":"lr"},{"id":"2502.17419","title":"From System 1 to System 2: A Survey of Reasoning Large Language Models","created":"2025-02-24","cited_by_count":320,"area":"lr"},{"id":"2404.18231","title":"From Persona to Personalization: A Survey on Role-Playing Language Agents","created":"2024-04-28","cited_by_count":212,"area":"agents"},{"id":"2505.19590","title":"Learning to Reason without External Rewards","created":"2025-05-26","cited_by_count":210,"area":"lr"},{"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,"area":"lr"},{"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":"2410.02603","title":"Agents' Room: Narrative Generation through Multi-step Collaboration","created":"2024-10-03","cited_by_count":57,"area":"agents"},{"id":"2508.14029","title":"Beyond Pass@1: Self-Play with Variational Problem Synthesis Sustains RLVR","created":"2025-08-19","cited_by_count":54,"area":"lr"},{"id":"2408.08862","title":"Visual Agents as Fast and Slow Thinkers","created":"2024-08-16","cited_by_count":53,"area":"lr"},{"id":"2509.07414","title":"Language Self-Play For Data-Free Training","created":"2025-09-09","cited_by_count":43,"area":"synth"},{"id":"2502.16235","title":"Dynamic Parallel Tree Search for Efficient LLM Reasoning","created":"2025-02-22","cited_by_count":42,"area":"lr"},{"id":"2410.06961","title":"Self-Boosting Large Language Models with Synthetic Preference Data","created":"2024-10-09","cited_by_count":40,"area":"alignment"},{"id":"2505.19683","title":"Large Language Models for Planning: A Comprehensive and Systematic Survey","created":"2025-05-26","cited_by_count":40,"area":"lr"},{"id":"2502.12853","title":"S$^2$R: Teaching LLMs to Self-verify and Self-correct via Reinforcement Learning","created":"2025-02-18","cited_by_count":39,"area":"lr"},{"id":"2506.07468","title":"Chasing Moving Targets with Online Self-Play Reinforcement Learning for Safer Language Models","created":"2025-06-09","cited_by_count":39,"area":"alignment"},{"id":"2505.24785","title":"EXP-Bench: Can AI Conduct AI Research Experiments?","created":"2025-05-30","cited_by_count":37,"area":null},{"id":"2510.18821","title":"Search Self-play: Pushing the Frontier of Agent Capability without Supervision","created":"2025-10-21","cited_by_count":34,"area":"agents"},{"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":"2412.06394","title":"GameArena: Evaluating LLM Reasoning through Live Computer Games","created":"2024-12-09","cited_by_count":32,"area":"lr"},{"id":"2408.01072","title":"A Survey on Self-play Methods in Reinforcement Learning","created":"2024-08-02","cited_by_count":26,"area":"deeprl"},{"id":"2502.05163","title":"Enhancing LLM Safety Through a Theoretical Minimax Game Lens","created":"2025-02-07","cited_by_count":19,"area":"safety"},{"id":"2408.10635","title":"Strategist: Self-improvement of LLM Decision Making via Bi-Level Tree Search","created":"2024-08-20","cited_by_count":17,"area":"synth"},{"id":"2502.09053","title":"Game Theory Meets Large Language Models: A Systematic Survey with Taxonomy and New Frontiers","created":"2025-02-13","cited_by_count":16,"area":null},{"id":"2510.05442","title":"Adversarial Reinforcement Learning for Large Language Model Agent Safety","created":"2025-10-06","cited_by_count":16,"area":"agents"},{"id":"2505.20259","title":"Lifelong Safety Alignment for Language Models","created":"2025-05-26","cited_by_count":15,"area":"alignment"},{"id":"2406.10977","title":"Toward Optimal LLM Alignments Using Two-Player Games","created":"2024-06-16","cited_by_count":13,"area":"alignment"},{"id":"2512.18160","title":"Propose, Solve, Verify: Self-Play Through Formal Verification","created":"2025-12-20","cited_by_count":13,"area":"synth"},{"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,"area":"agents"},{"id":"2504.19276","title":"Anyprefer: An Agentic Framework for Preference Data Synthesis","created":"2025-04-27","cited_by_count":10,"area":"agents"},{"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":"2503.01513","title":"Evaluation and Facilitation of Online Discussions in the LLM Era: A Survey","created":"2025-03-03","cited_by_count":9,"area":null},{"id":"2505.13636","title":"Incentivizing Truthful Language Models via Peer Elicitation Games","created":"2025-05-19","cited_by_count":9,"area":null},{"id":"2506.00539","title":"ARIA: Training Language Agents with Intention-Driven Reward Aggregation","created":"2025-05-31","cited_by_count":9,"area":"agents"},{"id":"2511.11881","title":"Better LLM Reasoning via Dual-Play","created":"2025-11-14","cited_by_count":8,"area":"lr"},{"id":"2602.00173","title":"Learning Robust Reasoning through Guided Adversarial Self-Play","created":"2026-01-30","cited_by_count":8,"area":"lr"},{"id":"2405.21040","title":"Direct Alignment of Language Models via Quality-Aware Self-Refinement","created":"2024-05-31","cited_by_count":7,"area":"alignment"},{"id":"2408.14853","title":"Atoxia: Red-teaming Large Language Models with Target Toxic Answers","created":"2024-08-27","cited_by_count":7,"area":"safety"},{"id":"2505.18218","title":"CoMet: Metaphor-Driven Covert Communication for Multi-Agent Language Games","created":"2025-05-23","cited_by_count":7,"area":"agents"},{"id":"2506.22920","title":"Improving Rationality in the Reasoning Process of Language Models through Self-playing Game","created":"2025-06-28","cited_by_count":7,"area":"lr"},{"id":"2510.03971","title":"What Can You Do When You Have Zero Rewards During RL?","created":"2025-10-04","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":"2506.06366","title":"AI Agent Behavioral Science","created":"2025-06-04","cited_by_count":6,"area":"agents"},{"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":"2601.10589","title":"Be Your Own Red Teamer: Safety Alignment via Self-Play and Reflective Experience Replay","created":"2026-01-15","cited_by_count":6,"area":"alignment"},{"id":"2509.03937","title":"SPFT-SQL: Enhancing Large Language Model for Text-to-SQL Parsing by Self-Play Fine-Tuning","created":"2025-09-04","cited_by_count":5,"area":"synth"},{"id":"2604.20051","title":"Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text","created":"2026-04-21","cited_by_count":5,"area":"synth"},{"id":"2410.15639","title":"Can Large Language Models Invent Algorithms to Improve Themselves?: Algorithm Discovery for Recursive Self-Improvement through Reinforcement Learning","created":"2024-10-21","cited_by_count":4,"area":"synth"},{"id":"2502.05400","title":"Dynamic Noise Preference Optimization: Self-Improvement of Large Language Models with Self-Synthetic Data","created":"2025-02-08","cited_by_count":4,"area":"alignment"},{"id":"2505.00031","title":"Learning to Plan Before Answering: Self-Teaching LLMs to Learn Abstract Plans for Problem Solving","created":"2025-04-28","cited_by_count":4,"area":"synth"},{"id":"2505.05445","title":"clem:todd: A Framework for the Systematic Benchmarking of LLM-Based Task-Oriented Dialogue System Realisations","created":"2025-05-08","cited_by_count":4,"area":null},{"id":"2508.02076","title":"Everyone Contributes! Incentivizing Strategic Cooperation in Multi-LLM Systems via Sequential Public Goods Games","created":"2025-08-04","cited_by_count":4,"area":null},{"id":"2505.05515","title":"Nature's Insight: A Novel Framework and Comprehensive Analysis of Agentic Reasoning Through the Lens of Neuroscience","created":"2025-05-07","cited_by_count":3,"area":"agents"},{"id":"2601.15047","title":"Game-Theoretic Lens on LLM-based Multi-Agent Systems","created":"2026-01-21","cited_by_count":3,"area":"lr"},{"id":"2603.10476","title":"Learning to Negotiate: Multi-Agent Deliberation for Collective Value Alignment in LLMs","created":"2026-03-11","cited_by_count":3,"area":"agents"},{"id":"2606.16771","title":"GD$^2$PO: Mitigating Multi-Reward Conflicts via Group-Dynamic reward-Decoupled Policy Optimization","created":"2026-06-15","cited_by_count":3,"area":"alignment"},{"id":"2504.08590","title":"Playpen: An Environment for Exploring Learning Through Conversational Interaction","created":"2025-04-11","cited_by_count":2,"area":"alignment"},{"id":"2601.16276","title":"GameTalk: Training LLMs for Strategic Conversation","created":"2026-01-22","cited_by_count":2,"area":null},{"id":"2602.00127","title":"ALIGN: Aligned Delegation with Performance Guarantees for Multi-Agent LLM Reasoning","created":"2026-01-28","cited_by_count":2,"area":"lr"},{"id":"2603.00918","title":"Improving Text-to-Image Generation with Intrinsic Self-Confidence Rewards","created":"2026-03-01","cited_by_count":2,"area":"alignment"},{"id":"2603.04364","title":"Dual-Modality Multi-Stage Adversarial Safety Training: Robustifying Multimodal Web Agents Against Cross-Modal Attacks","created":"2026-03-04","cited_by_count":2,"area":"agents"},{"id":"2605.05702","title":"Knowledge-Graph Paths as Intermediate Supervision for Self-Evolving Search Agents","created":"2026-05-07","cited_by_count":2,"area":"agents"},{"id":"2408.12333","title":"GRATR: Zero-Shot Evidence Graph Retrieval-Augmented Trustworthiness Reasoning","created":"2024-08-22","cited_by_count":1,"area":"lr"},{"id":"2508.08719","title":"IROTE: Human-like Traits Elicitation of Large Language Model via In-Context Self-Reflective Optimization","created":"2025-08-12","cited_by_count":1,"area":null},{"id":"2510.15772","title":"Self-evolving expertise in complex non-verifiable subject domains: dialogue as implicit meta-RL","created":"2025-10-17","cited_by_count":1,"area":"lr"},{"id":"2510.16761","title":"Enhancing Language Agent Strategic Reasoning through Self-Play in Adversarial Games","created":"2025-10-19","cited_by_count":1,"area":"agents"},{"id":"2601.04516","title":"LinguaGame: A Linguistically Grounded Game-Theoretic Paradigm for Multi-Agent Dialogue Generation","created":"2026-01-08","cited_by_count":1,"area":"agents"},{"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":"2608.10299","title":"Co-Evolution in Agentic Systems: Toward Self-Directed Evolution Beyond Human Design","created":"2026-08-10","cited_by_count":1,"area":"agents"},{"id":"2509.24274","title":"Adversarial Reinforcement Learning Framework for ESP Cheater Simulation","created":"2025-09-29","cited_by_count":0,"area":"deeprl"},{"id":"2509.26461","title":"CreAgentive: An Agent Workflow Driven Multi-Category Creative Generation Engine","created":"2025-09-30","cited_by_count":0,"area":"agents"},{"id":"2512.07474","title":"Living the Novel: A System for Generating Self-Training Timeline-Aware Conversational Agents from Novels","created":"2025-12-08","cited_by_count":0,"area":"agents"},{"id":"2601.19122","title":"Exploring Weaknesses in Function Call Models via Reinforcement Learning: An Adversarial Data Augmentation Approach","created":"2026-01-27","cited_by_count":0,"area":"lr"},{"id":"2604.17312","title":"A Survey of Reinforcement Learning for Large Language Models under Data Scarcity: Challenges and Solutions","created":"2026-04-19","cited_by_count":0,"area":"lr"},{"id":"2605.09922","title":"Team-Based Self-Play With Dual Adaptive Weighting for Fine-Tuning LLMs","created":"2026-05-11","cited_by_count":0,"area":"synth"},{"id":"2605.17278","title":"A2RBench: An Automatic Paradigm for Formally Verifiable Abstract Reasoning Benchmark Generation","created":"2026-05-17","cited_by_count":0,"area":"lr"},{"id":"2605.27832","title":"Playing with Words, Improving with Rewards: Training Language Models for Creative Association","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2606.05002","title":"GARL: Game-Theoretic Reinforcement Learning for Multi-Agent Strategic Prioritisation","created":"2026-06-03","cited_by_count":0,"area":"agents"},{"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":"2608.27910","title":"AI Alignment through a Game-theoretic Lens: A Survey","created":"2026-08-28","cited_by_count":0,"area":"alignment"},{"id":"2610.04261","title":"Playing social deduction games with reinforcement fine-tuned large language models","created":"2026-10-03","cited_by_count":0,"area":null},{"id":"2610.13995","title":"GameSmith: Scaling Zero-Sum Self-Play with Synthesised Games","created":"2026-09-26","cited_by_count":0,"area":"synth"},{"id":"2610.19422","title":"AgentSafeEvo: Adversarial Co-Evolution for LLM Agent Safety","created":"2026-10-14","cited_by_count":0,"area":"agents"}],"next_cursor":null}