{"total":14,"rows":[{"id":"2504.15585","title":"A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment","created":"2025-04-22","cited_by_count":116,"area":"lr"},{"id":"2601.12538","title":"A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agents","created":"2026-01-18","cited_by_count":50,"area":"lr"},{"id":"2506.01341","title":"TurnBench-MS: A Benchmark for Evaluating Multi-Turn, Multi-Step Reasoning in Large Language Models","created":"2025-06-02","cited_by_count":13,"area":"lr"},{"id":"2505.14552","title":"KORGym: A Dynamic Game Platform for LLM Reasoning Evaluation","created":"2025-05-20","cited_by_count":7,"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":"2506.05813","title":"MAPLE: Multi-Agent Adaptive Planning with Long-Term Memory for Table Reasoning","created":"2025-06-06","cited_by_count":4,"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":"2508.16072","title":"InMind: Evaluating LLMs in Capturing and Applying Individual Human Reasoning Styles","created":"2025-08-22","cited_by_count":2,"area":"lr"},{"id":"2512.14118","title":"CogMem: A Cognitive Memory Architecture for Sustained Multi-Turn Reasoning in Large Language Models","created":"2025-12-16","cited_by_count":2,"area":"lr"},{"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":"2506.10264","title":"WGSR-Bench: Wargame-based Game-theoretic Strategic Reasoning Benchmark for Large Language Models","created":"2025-06-12","cited_by_count":1,"area":"lr"},{"id":"2604.13592","title":"Foresight Optimization for Strategic Reasoning in Large Language Models","created":"2026-04-15","cited_by_count":0,"area":"lr"},{"id":"2604.16022","title":"SocialGrid: A Benchmark for Planning and Social Reasoning in Embodied Multi-Agent Systems","created":"2026-04-17","cited_by_count":0,"area":"lr"},{"id":"2606.18950","title":"RTSGameBench: An RTS Benchmark for Strategic Reasoning by Vision-Language Models","created":"2026-06-17","cited_by_count":0,"area":"lr"}],"next_cursor":null}