{"total":23,"rows":[{"id":"2505.08638","title":"TRAIL: Trace Reasoning and Agentic Issue Localization","created":"2025-05-13","cited_by_count":104,"area":"lr"},{"id":"2503.12349","title":"SPIN-Bench: How Well Do LLMs Plan Strategically and Reason Socially?","created":"2025-03-16","cited_by_count":24,"area":"lr"},{"id":"2505.07215","title":"Measuring General Intelligence with Generated Games","created":"2025-05-12","cited_by_count":24,"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":"2412.11373","title":"Codenames as a Benchmark for Large Language Models","created":"2024-12-16","cited_by_count":8,"area":"lr"},{"id":"2603.07379","title":"SoK: Agentic Retrieval-Augmented Generation (RAG): Taxonomy, Architectures, Evaluation, and Research Directions","created":"2026-03-07","cited_by_count":8,"area":"lr"},{"id":"2602.00528","title":"How Far Are LLMs from Professional Poker Players? Revisiting Game-Theoretic Reasoning with Agentic Tool Use","created":"2026-01-31","cited_by_count":7,"area":"lr"},{"id":"2506.12012","title":"Tracing LLM Reasoning Processes with Strategic Games: A Framework for Planning, Revision, and Resource-Constrained Decision Making","created":"2025-06-13","cited_by_count":5,"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":"2506.10209","title":"TTT-Bench: A Benchmark for Evaluating Reasoning Ability with Simple and Novel Tic-Tac-Toe-style Games","created":"2025-06-11","cited_by_count":3,"area":"lr"},{"id":"2601.15047","title":"Game-Theoretic Lens on LLM-based Multi-Agent Systems","created":"2026-01-21","cited_by_count":3,"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":"2506.00577","title":"Reasoning Like an Economist: Post-Training on Economic Problems Induces Strategic Generalization in LLMs","created":"2025-05-31","cited_by_count":2,"area":"lr"},{"id":"2603.20209","title":"Children's Intelligence Tests Pose Challenges for MLLMs? KidGym: A 2D Grid-Based Reasoning Benchmark for MLLMs","created":"2026-03-02","cited_by_count":2,"area":"lr"},{"id":"2408.12333","title":"GRATR: Zero-Shot Evidence Graph Retrieval-Augmented Trustworthiness Reasoning","created":"2024-08-22","cited_by_count":1,"area":"lr"},{"id":"2508.11944","title":"CHBench: A Cognitive Hierarchy Benchmark for Evaluating Strategic Reasoning Capability of LLMs","created":"2025-08-16","cited_by_count":1,"area":"lr"},{"id":"2508.19035","title":"Investigating Advanced Reasoning of Large Language Models via Black-Box Environment Interaction","created":"2025-08-26","cited_by_count":1,"area":"lr"},{"id":"2602.08041","title":"Implicit Strategic Optimization: Rethinking Long-Horizon Decision-Making in Adversarial Poker Environments","created":"2026-02-08","cited_by_count":1,"area":"lr"},{"id":"2604.05681","title":"LUDOBENCH: Evaluating LLM Behavioural Decision-Making Through Spot-Based Board Game Scenarios in Ludo","created":"2026-04-07","cited_by_count":1,"area":"lr"},{"id":"2607.22732","title":"Spatial Reasoning in LLM Game Agents: Impact of Causal Context and Multi-Step Planning","created":"2026-07-22","cited_by_count":1,"area":"lr"},{"id":"2605.23238","title":"GENSTRAT: Toward a Science of Strategic Reasoning in Large Language Models","created":"2026-05-22","cited_by_count":0,"area":"lr"},{"id":"2606.00476","title":"Doing What They Say, Not What They Reason: Locating the Faithfulness Gap in LLM Agents","created":"2026-05-30","cited_by_count":0,"area":"lr"},{"id":"2606.24391","title":"Age of LLM: A Strategic 1v1 Benchmark for Reasoning, Diplomacy and Reliability of Large Language Models under Fog of War","created":"2026-06-23","cited_by_count":0,"area":"lr"}],"next_cursor":null}