{"total":18,"rows":[{"id":"2311.10537","title":"MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoning","created":"2023-11-16","cited_by_count":316,"area":"lr"},{"id":"2509.08827","title":"A Survey of Reinforcement Learning for Large Reasoning Models","created":"2025-09-10","cited_by_count":180,"area":"lr"},{"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,"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":"2602.06176","title":"Large Language Model Reasoning Failures","created":"2026-02-05","cited_by_count":21,"area":"lr"},{"id":"2508.16861","title":"Learning from Diverse Reasoning Paths with Routing and Collaboration","created":"2025-08-23","cited_by_count":12,"area":"lr"},{"id":"2504.14520","title":"Meta-Thinking in LLMs via Multi-Agent Reinforcement Learning: A Survey","created":"2025-04-20","cited_by_count":10,"area":"lr"},{"id":"2505.04364","title":"Benchmarking LLMs' Swarm intelligence","created":"2025-05-07","cited_by_count":10,"area":"lr"},{"id":"2506.07232","title":"Learn as Individuals, Evolve as a Team: Multi-agent LLMs Adaptation in Embodied Environments","created":"2025-06-08","cited_by_count":4,"area":"lr"},{"id":"2506.20664","title":"The Decrypto Benchmark for Multi-Agent Reasoning and Theory of Mind","created":"2025-06-25","cited_by_count":4,"area":"lr"},{"id":"2404.15515","title":"ToM-LM: Delegating Theory of Mind Reasoning to External Symbolic Executors in Large Language Models","created":"2024-04-23","cited_by_count":2,"area":"lr"},{"id":"2512.09548","title":"Supporting Dynamic Agentic Workloads: How Data and Agents Interact","created":"2025-12-10","cited_by_count":2,"area":"lr"},{"id":"2510.13395","title":"Doing Things with Words: Rethinking Theory of Mind Simulation in Large Language Models","created":"2025-10-15","cited_by_count":1,"area":"lr"},{"id":"2601.12323","title":"MARO: Learning Stronger Reasoning from Social Interaction","created":"2026-01-18","cited_by_count":1,"area":"lr"},{"id":"2604.20658","title":"Cooperative Profiles Predict Multi-Agent LLM Team Performance in AI for Science Workflows","created":"2026-04-22","cited_by_count":1,"area":"lr"},{"id":"2605.08478","title":"When Independent Sampling Outperforms Agentic Reasoning","created":"2026-05-08","cited_by_count":0,"area":"lr"},{"id":"2609.34342","title":"SAGE: Structured Strategic Reasoning for Efficient LLM Game Playing","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2609.39727","title":"OverForge: Reasoning Through Strategies and Tactics Helps Cooperative Lifelong Adaptation","created":"2026-09-30","cited_by_count":0,"area":"lr"}],"next_cursor":null}