{"total":15,"rows":[{"id":"2509.08827","title":"A Survey of Reinforcement Learning for Large Reasoning Models","created":"2025-09-10","cited_by_count":180,"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":"2509.25052","title":"Cogito, Ergo Ludo: An Agent that Learns to Play by Reasoning and Planning","created":"2025-09-29","cited_by_count":12,"area":"lr"},{"id":"2508.03368","title":"Game Reasoning Arena: A Framework and Benchmark for Assessing Reasoning Capabilities of Large Language Models via Game Play","created":"2025-08-05","cited_by_count":11,"area":"lr"},{"id":"2605.29512","title":"MINDGAMES: A Live Arena for Evaluating Social and Strategic Reasoning in Multi-Agent LLMs","created":"2026-05-28","cited_by_count":5,"area":"lr"},{"id":"2605.14537","title":"Cattle Trade: A Multi-Agent Benchmark for LLM Bluffing, Bidding, and Bargaining","created":"2026-05-14","cited_by_count":3,"area":"lr"},{"id":"2601.20856","title":"SokoBench: Evaluating Long-Horizon Planning and Reasoning in Large Language Models","created":"2026-01-28","cited_by_count":2,"area":"lr"},{"id":"2604.20043","title":"TriEx: A Game-based Tri-View Framework for Explaining Internal Reasoning in Multi-Agent LLMs","created":"2026-04-21","cited_by_count":1,"area":"lr"},{"id":"2509.17978","title":"The STAR-XAI Protocol: A Framework for Inducing and Verifying Agency, Reasoning, and Reliability in AI Agents","created":"2025-09-22","cited_by_count":0,"area":"lr"},{"id":"2602.19160","title":"Reasoning Capabilities of Large Language Models. Lessons Learned from General Game Playing","created":"2026-02-22","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":"2609.30936","title":"Self-Play Search Distillation for Large Language Model Reasoning","created":"2026-09-25","cited_by_count":0,"area":"lr"},{"id":"2609.34214","title":"GlyphBench: A Playground for Language-Model Reinforcement Learning","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2609.34769","title":"LongPuzzleBench: Evaluating GUI Agents on Long-Horizon Visual Puzzles","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2610.18834","title":"Game2Real-Bench: Do Toy Games Reveal and Transfer to Real-World Visual Reasoning?","created":"2026-10-13","cited_by_count":0,"area":"lr"}],"next_cursor":null}