{"total":17,"rows":[{"id":"2503.01935","title":"MultiAgentBench: Evaluating the Collaboration and Competition of LLM agents","created":"2025-03-03","cited_by_count":178,"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":"2312.14890","title":"NPHardEval: Dynamic Benchmark on Reasoning Ability of Large Language Models via Complexity Classes","created":"2023-12-22","cited_by_count":79,"area":"lr"},{"id":"2501.13381","title":"Do as We Do, Not as You Think: the Conformity of Large Language Models","created":"2025-01-23","cited_by_count":53,"area":"lr"},{"id":"2312.04854","title":"Learning to Break: Knowledge-Enhanced Reasoning in Multi-Agent Debate System","created":"2023-12-08","cited_by_count":26,"area":"lr"},{"id":"2406.02787","title":"Disentangling Logic: The Role of Context in Large Language Model Reasoning Capabilities","created":"2024-06-04","cited_by_count":22,"area":"lr"},{"id":"2402.01521","title":"K-Level Reasoning: Establishing Higher Order Beliefs in Large Language Models for Strategic Reasoning","created":"2024-02-02","cited_by_count":21,"area":"lr"},{"id":"2410.20007","title":"Cooperative Strategic Planning Enhances Reasoning Capabilities in Large Language Models","created":"2024-10-25","cited_by_count":6,"area":"lr"},{"id":"2407.06112","title":"Enhancing Language Model Rationality with Bi-Directional Deliberation Reasoning","created":"2024-07-08","cited_by_count":5,"area":"lr"},{"id":"2410.01696","title":"CreDes: Causal Reasoning Enhancement and Dual-End Searching for Solving Long-Range Reasoning Problems using LLMs","created":"2024-10-02","cited_by_count":5,"area":"lr"},{"id":"2505.20246","title":"On Path to Multimodal Historical Reasoning: HistBench and HistAgent","created":"2025-05-26","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":"2510.17491","title":"Empowering Real-World: A Survey on the Technology, Practice, and Evaluation of LLM-driven Industry Agents","created":"2025-10-20","cited_by_count":2,"area":"lr"},{"id":"2605.17079","title":"Can LLMs Think Like Consumers? Benchmarking Crowd-Level Reaction Reconstruction with ConsumerSimBench","created":"2026-05-16","cited_by_count":1,"area":"lr"},{"id":"2606.11082","title":"The Shibboleth Effect: Auditing the Cross-Lingual Distributional Skew of Large Language Models","created":"2026-06-09","cited_by_count":0,"area":"lr"},{"id":"2607.28146","title":"Can Agents Deceive? Evaluating Reasoning and Deception in ParliamentBench using a Social Deduction Game","created":"2026-07-30","cited_by_count":0,"area":"lr"},{"id":"2608.19689","title":"Rethinking the Evaluation and Optimization of LLM-Based Social Simulation","created":"2026-08-20","cited_by_count":0,"area":"lr"}],"next_cursor":null}