{"total":95,"rows":[{"id":"2505.08638","title":"TRAIL: Trace Reasoning and Agentic Issue Localization","created":"2025-05-13","cited_by_count":104,"area":"lr"},{"id":"2505.15146","title":"lmgame-Bench: How Good are LLMs at Playing Games?","created":"2025-05-21","cited_by_count":55,"area":null},{"id":"2412.01441","title":"LMAct: A Benchmark for In-Context Imitation Learning with Long Multimodal Demonstrations","created":"2024-12-02","cited_by_count":32,"area":"offlinerl"},{"id":"2506.03610","title":"Orak: A Foundational Benchmark for Training and Evaluating LLM Agents on Diverse Video Games","created":"2025-06-04","cited_by_count":31,"area":"agents"},{"id":"2504.11442","title":"TextArena","created":"2025-04-15","cited_by_count":27,"area":null},{"id":"2510.04542","title":"Code World Models for General Game Playing","created":"2025-10-06","cited_by_count":26,"area":"wm"},{"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":"2412.03920","title":"A Survey on Large Language Model-Based Social Agents in Game-Theoretic Scenarios","created":"2024-12-05","cited_by_count":23,"area":"agents"},{"id":"2503.06047","title":"DSGBench: A Diverse Strategic Game Benchmark for Evaluating LLM-based Agents in Complex Decision-Making Environments","created":"2025-03-08","cited_by_count":23,"area":"agents"},{"id":"2407.07796","title":"Evaluating Large Language Models with Grid-Based Game Competitions: An Extensible LLM Benchmark and Leaderboard","created":"2024-07-10","cited_by_count":22,"area":null},{"id":"2506.04651","title":"Agents of Change: Self-Evolving LLM Agents for Strategic Planning","created":"2025-06-05","cited_by_count":21,"area":"agents"},{"id":"2602.05073","title":"Uncertainty Quantification in LLM Agents: Foundations, Emerging Challenges, and Opportunities","created":"2026-02-04","cited_by_count":20,"area":"agents"},{"id":"2503.02358","title":"Are Large Vision Language Models Good Game Players?","created":"2025-03-04","cited_by_count":19,"area":"mllm"},{"id":"2412.12480","title":"Subversion Strategy Eval: Can language models statelessly strategize to subvert control protocols?","created":"2024-12-17","cited_by_count":15,"area":null},{"id":"2506.11102","title":"Evolutionary Perspectives on the Evaluation of LLM-Based AI Agents: A Comprehensive Survey","created":"2025-06-06","cited_by_count":13,"area":"agents"},{"id":"2605.17637","title":"WebGameBench: Requirement-to-Application Evaluation for Coding Agents via Browser-Native Games","created":"2026-05-17","cited_by_count":12,"area":"agents"},{"id":"2504.06148","title":"V-MAGE: A Game Evaluation Framework for Assessing Vision-Centric Capabilities in Multimodal Large Language Models","created":"2025-04-08","cited_by_count":11,"area":"mllm"},{"id":"2507.11633","title":"General Modular Harness for LLM Agents in Multi-Turn Gaming Environments","created":"2025-07-15","cited_by_count":11,"area":"agents"},{"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":"2505.00049","title":"Humanizing LLMs: A Survey of Psychological Measurements with Tools, Datasets, and Human-Agent Applications","created":"2025-04-30","cited_by_count":10,"area":"agents"},{"id":"2412.11373","title":"Codenames as a Benchmark for Large Language Models","created":"2024-12-16","cited_by_count":8,"area":"lr"},{"id":"2601.08462","title":"M3-BENCH: Process-Aware Evaluation of LLM Agents' Social Behaviors in Mixed-Motive Games","created":"2026-01-13","cited_by_count":8,"area":"agents"},{"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":"2606.12191","title":"Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application","created":"2026-06-10","cited_by_count":8,"area":"agents"},{"id":"2508.07485","title":"Democratizing Diplomacy: A Harness for Evaluating Any Large Language Model on Full-Press Diplomacy","created":"2025-08-10","cited_by_count":7,"area":null},{"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":"2503.10673","title":"ZeroSumEval: An Extensible Framework For Scaling LLM Evaluation with Inter-Model Competition","created":"2025-03-10","cited_by_count":5,"area":null},{"id":"2504.12562","title":"ZeroSumEval: Scaling LLM Evaluation with Inter-Model Competition","created":"2025-04-17","cited_by_count":5,"area":null},{"id":"2505.15068","title":"ModelingAgent: Bridging LLMs and Mathematical Modeling for Real-World Challenges","created":"2025-05-21","cited_by_count":5,"area":null},{"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":"2412.12409","title":"Improving Cooperation in Language Games with Bayesian Inference and the Cognitive Hierarchy","created":"2024-12-16","cited_by_count":4,"area":null},{"id":"2502.10760","title":"Why is prompting hard? Understanding prompts on binary sequence predictors","created":"2025-02-15","cited_by_count":4,"area":null},{"id":"2505.23006","title":"A Practical Approach for Building Production-Grade Conversational Agents with Workflow Graphs","created":"2025-05-29","cited_by_count":4,"area":"agents"},{"id":"2510.05748","title":"Communication Enables Cooperation in LLM Agents: A Comparison with Curriculum-Based Approaches","created":"2025-10-07","cited_by_count":4,"area":"agents"},{"id":"2512.18564","title":"Vox Deorum: A Hybrid LLM Architecture for 4X / Grand Strategy Game AI -- Lessons from Civilization V","created":"2025-12-21","cited_by_count":4,"area":null},{"id":"2502.07128","title":"Cardiverse: Harnessing LLMs for Novel Card Game Prototyping","created":"2025-02-10","cited_by_count":3,"area":null},{"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":"2507.08491","title":"A Third Paradigm for LLM Evaluation: Dialogue Game-Based Evaluation using clembench","created":"2025-07-11","cited_by_count":3,"area":null},{"id":"2601.09503","title":"What Do LLM Agents Know About Their World? Task2Quiz: A Paradigm for Studying Environment Understanding","created":"2026-01-14","cited_by_count":3,"area":"agents"},{"id":"2601.15047","title":"Game-Theoretic Lens on LLM-based Multi-Agent Systems","created":"2026-01-21","cited_by_count":3,"area":"lr"},{"id":"2605.09965","title":"Towards Generalist Game Players: An Investigation of Foundation Models in the Game Multiverse","created":"2026-05-11","cited_by_count":3,"area":null},{"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":"2505.20120","title":"Agents Require Metacognitive and Strategic Reasoning to Succeed in the Coming Labor Markets","created":"2025-05-26","cited_by_count":2,"area":null},{"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":"2508.08382","title":"UrzaGPT: LoRA-Tuned Large Language Models for Card Selection in Collectible Card Games","created":"2025-08-11","cited_by_count":2,"area":null},{"id":"2509.17192","title":"Shall We Play a Game? Language Models for Open-ended Wargames","created":"2025-09-21","cited_by_count":2,"area":null},{"id":"2602.13214","title":"BotzoneBench: Scalable LLM Evaluation via Graded AI Anchors","created":"2026-01-22","cited_by_count":2,"area":null},{"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":"2604.07733","title":"CivBench: Progress-Based Evaluation for LLMs' Strategic Decision-Making in Civilization V","created":"2026-04-09","cited_by_count":2,"area":"agents"},{"id":"2606.05793","title":"CollabBench: Benchmarking and Unleashing Collaborative Ability of LLMs with Diverse Players via Proactive Engagement","created":"2026-06-04","cited_by_count":2,"area":"agents"},{"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":"2509.17694","title":"Evaluating LLM-Generated Versus Human-Authored Responses in Role-Play Dialogues","created":"2025-09-22","cited_by_count":1,"area":null},{"id":"2510.16761","title":"Enhancing Language Agent Strategic Reasoning through Self-Play in Adversarial Games","created":"2025-10-19","cited_by_count":1,"area":"agents"},{"id":"2510.16774","title":"Learning to play: A Multimodal Agent for 3D Game-Play","created":"2025-10-19","cited_by_count":1,"area":null},{"id":"2512.00834","title":"SemAgent: Semantic-Driven Agentic AI Empowered Trajectory Prediction in Vehicular Networks","created":"2025-11-30","cited_by_count":1,"area":"agents"},{"id":"2602.05183","title":"Data-Centric Interpretability for LLM-based Multi-Agent Reinforcement Learning","created":"2026-02-05","cited_by_count":1,"area":"agents"},{"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":"2605.06066","title":"Causal Reinforcement Learning for Complex Card Games: A Magic The Gathering Benchmark","created":"2026-05-07","cited_by_count":1,"area":"wm"},{"id":"2605.22826","title":"Evaluating Large Language Models in a Complex Hidden Role Game","created":"2026-04-09","cited_by_count":1,"area":null},{"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":"2608.25832","title":"Skill Issue: Are Skills Language-Invariant in LLMs?","created":"2026-08-26","cited_by_count":1,"area":null},{"id":"2512.19210","title":"Observer, Not Player: Simulating Theory of Mind in LLMs through Game Observation","created":"2025-12-22","cited_by_count":0,"area":null},{"id":"2512.21024","title":"Policy-Conditioned Policies for Multi-Agent Task Solving","created":"2025-12-24","cited_by_count":0,"area":"agents"},{"id":"2601.08742","title":"Inferring Latent Intentions: Attributional Natural Language Inference in LLM Agents","created":"2026-01-13","cited_by_count":0,"area":"agents"},{"id":"2601.09017","title":"Multicultural Spyfall: Assessing LLMs through Dynamic Multilingual Social Deduction Game","created":"2026-01-13","cited_by_count":0,"area":null},{"id":"2601.22345","title":"Failing to Explore: Language Models on Interactive Tasks","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2603.01260","title":"MOSAIC: A Universal Agent-Level Interface for Cross-Paradigm Agent Mixing and Human-AI Collaboration","created":"2026-03-01","cited_by_count":0,"area":"agents"},{"id":"2604.06562","title":"On Emotion-Sensitive Decision Making of Small Language Model Agents","created":"2026-04-08","cited_by_count":0,"area":"agents"},{"id":"2604.17244","title":"DORA Explorer: Improving the Exploration Ability of LLMs Without Training","created":"2026-04-19","cited_by_count":0,"area":null},{"id":"2604.25067","title":"Frontier Coding Agents Can Now Implement an AlphaZero Self-Play Machine Learning Pipeline For Connect Four That Performs Comparably to an External Solver","created":"2026-04-27","cited_by_count":0,"area":"agents"},{"id":"2605.12824","title":"Mechanism Plausibility in Generative Agent-Based Modeling","created":"2026-05-12","cited_by_count":0,"area":"agents"},{"id":"2605.22238","title":"Evaluating Large Language Models as Live Strategic Agents: Provider Performance, Hybrid Decomposition, and Operational Gaps in Timed Risk Play","created":"2026-05-21","cited_by_count":0,"area":"agents"},{"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":"2606.05002","title":"GARL: Game-Theoretic Reinforcement Learning for Multi-Agent Strategic Prioritisation","created":"2026-06-03","cited_by_count":0,"area":"agents"},{"id":"2606.19308","title":"Enhancing Decision-Making with Large Language Models through Multi-Agent Fictitious Play","created":"2026-06-17","cited_by_count":0,"area":"agents"},{"id":"2606.19338","title":"Beyond the Current Observation: Evaluating Multimodal Large Language Models in Controllable Non-Markov Games","created":"2026-06-17","cited_by_count":0,"area":"mllm"},{"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"},{"id":"2606.26094","title":"RevengeBench: Reverse Engineering Code-Space Policies from Behavioral Experiments","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2606.27397","title":"SidConArena: An Environment Evaluating Agents in Open-Ended,Positive-Sum Bargaining Game","created":"2026-06-24","cited_by_count":0,"area":"agents"},{"id":"2608.07490","title":"Experience-Sensitive Game Learning: A Behavioral Study of Humans and Language Agents","created":"2026-06-15","cited_by_count":0,"area":"agents"},{"id":"2608.14613","title":"Do LLM Agents Negotiate Rationally? A Mechanism-Design Framework for Verifiable Multi-Agent Interaction over A2A/MCP","created":"2026-07-10","cited_by_count":0,"area":"agents"},{"id":"2609.02459","title":"CivBench: A Long-Horizon Benchmark for Tool-Mediated Agents in Civilization VI","created":"2026-09-02","cited_by_count":0,"area":"agents"},{"id":"2609.16189","title":"Position: AI Is Not Ready for Strategic Conflicts","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2609.34710","title":"FromPitch2Board: Benchmarking LLM Agents in Long-Horizon Football Management","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2610.02425","title":"Finding the Move Is Not Winning the Game: XiangqiBench for Closed-Loop Evaluation of LLM Agents","created":"2026-10-01","cited_by_count":0,"area":"agents"},{"id":"2610.04977","title":"Do LLMs Understand Sequential Structure? A Controlled Study of Inference and Generation","created":"2026-10-04","cited_by_count":0,"area":null},{"id":"2610.12341","title":"Can AI Agents Learn Their Way to the Top? Evaluating Heuristic Learning in a Long-Running Game Agent Competition","created":"2026-10-08","cited_by_count":0,"area":"deeprl"},{"id":"2610.13995","title":"GameSmith: Scaling Zero-Sum Self-Play with Synthesised Games","created":"2026-09-26","cited_by_count":0,"area":"synth"},{"id":"2610.19213","title":"PREFER: From Player Experience to Personalized Game Refinement","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}