{"total":120,"rows":[{"id":"2504.01990","title":"Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems","created":"2025-03-31","cited_by_count":126,"area":"agents"},{"id":"2404.16698","title":"Cooperate or Collapse: Emergence of Sustainable Cooperation in a Society of LLM Agents","created":"2024-04-25","cited_by_count":125,"area":"wm"},{"id":"2410.08948","title":"Emergent social conventions and collective bias in LLM populations","created":"2024-10-11","cited_by_count":123,"area":null},{"id":"2503.23037","title":"Agentic Large Language Models, a survey","created":"2025-03-29","cited_by_count":108,"area":"agents"},{"id":"2506.24119","title":"SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning","created":"2025-06-30","cited_by_count":100,"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":"2406.06613","title":"GameBench: Evaluating Strategic Reasoning Abilities of LLM Agents","created":"2024-06-07","cited_by_count":95,"area":"lr"},{"id":"2603.03329","title":"AutoHarness: improving LLM agents by automatically synthesizing a code harness","created":"2026-02-10","cited_by_count":76,"area":"agents"},{"id":"2403.11807","title":"How Far Are We on the Decision-Making of LLMs? Evaluating LLMs' Gaming Ability in Multi-Agent Environments","created":"2024-03-18","cited_by_count":67,"area":"agents"},{"id":"2407.00499","title":"ConU: Conformal Uncertainty in Large Language Models with Correctness Coverage Guarantees","created":"2024-06-29","cited_by_count":65,"area":null},{"id":"2406.13605","title":"Nicer Than Humans: How do Large Language Models Behave in the Prisoner's Dilemma?","created":"2024-06-19","cited_by_count":63,"area":null},{"id":"2411.05990","title":"Game-theoretic LLM: Agent Workflow for Negotiation Games","created":"2024-11-08","cited_by_count":56,"area":"agents"},{"id":"2410.15326","title":"A Survey of Uncertainty Estimation in LLMs: Theory Meets Practice","created":"2024-10-20","cited_by_count":55,"area":null},{"id":"2506.17419","title":"UProp: Investigating the Uncertainty Propagation of LLMs in Multi-Step Agentic Decision-Making","created":"2025-06-20","cited_by_count":42,"area":"agents"},{"id":"2410.01639","title":"Moral Alignment for LLM Agents","created":"2024-10-02","cited_by_count":39,"area":"agents"},{"id":"2503.15888","title":"Parameters vs. Context: Fine-Grained Control of Knowledge Reliance in Language Models","created":"2025-03-20","cited_by_count":39,"area":"rag"},{"id":"2505.13426","title":"G1: Bootstrapping Perception and Reasoning Abilities of Vision-Language Model via Reinforcement Learning","created":"2025-05-19","cited_by_count":29,"area":"lr"},{"id":"2504.11442","title":"TextArena","created":"2025-04-15","cited_by_count":27,"area":null},{"id":"2502.00290","title":"Estimating LLM Uncertainty with Evidence","created":"2025-02-01","cited_by_count":26,"area":null},{"id":"2410.10479","title":"TMGBench: A Systematic Game Benchmark for Evaluating Strategic Reasoning Abilities of LLMs","created":"2024-10-14","cited_by_count":24,"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":"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":"2502.17214","title":"CoT-UQ: Improving Response-wise Uncertainty Quantification in LLMs with Chain-of-Thought","created":"2025-02-24","cited_by_count":23,"area":"lr"},{"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":"2405.05248","title":"LLMs with Personalities in Multi-issue Negotiation Games","created":"2024-05-08","cited_by_count":22,"area":null},{"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":"2410.05254","title":"GLEE: A Unified Framework and Benchmark for Language-based Economic Environments","created":"2024-10-07","cited_by_count":20,"area":null},{"id":"2412.06681","title":"Toward LLM-Agent-Based Modeling of Transportation Systems: A Conceptual Framework","created":"2024-12-09","cited_by_count":19,"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":"2607.13104","title":"Self-Improvements in Modern Agentic Systems: A Survey","created":"2026-07-14","cited_by_count":19,"area":"agents"},{"id":"2402.14259","title":"Word-Sequence Entropy: Towards Uncertainty Estimation in Free-Form Medical Question Answering Applications and Beyond","created":"2024-02-22","cited_by_count":18,"area":null},{"id":"2502.20432","title":"LLM Strategic Reasoning: Agentic Study through Behavioral Game Theory","created":"2025-02-27","cited_by_count":17,"area":"lr"},{"id":"2510.22422","title":"Group size effects and collective misalignment in LLM multi-agent systems","created":"2025-10-25","cited_by_count":16,"area":"agents"},{"id":"2407.01505","title":"Self-Cognition in Large Language Models: An Exploratory Study","created":"2024-07-01","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":"2506.07388","title":"Shapley-Coop: Credit Assignment for Emergent Cooperation in Self-Interested LLM Agents","created":"2025-06-09","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":"2503.18825","title":"EconEvals: Benchmarks and Litmus Tests for Economic Decision-Making by LLM Agents","created":"2025-03-24","cited_by_count":10,"area":"agents"},{"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":"2505.20047","title":"Grammars of Formal Uncertainty: When to Trust LLMs in Automated Reasoning Tasks","created":"2025-05-26","cited_by_count":10,"area":"lr"},{"id":"2605.13909","title":"TERMS-Bench: Diagnosing LLM Negotiation Agents Beyond Deal Rate","created":"2026-05-13","cited_by_count":9,"area":"agents"},{"id":"2405.20859","title":"clembench-2024: A Challenging, Dynamic, Complementary, Multilingual Benchmark and Underlying Flexible Framework for LLMs as Multi-Action Agents","created":"2024-05-31","cited_by_count":8,"area":"agents"},{"id":"2409.07641","title":"SimulBench: Evaluating Language Models with Creative Simulation Tasks","created":"2024-09-11","cited_by_count":8,"area":null},{"id":"2506.20353","title":"DipSVD: Dual-importance Protected SVD for Efficient LLM Compression","created":"2025-06-25","cited_by_count":8,"area":null},{"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":"2406.12084","title":"When Reasoning Meets Information Aggregation: A Case Study with Sports Narratives","created":"2024-06-17","cited_by_count":7,"area":"lr"},{"id":"2408.05241","title":"Large Model Strategic Thinking, Small Model Efficiency: Transferring Theory of Mind in Large Language Models","created":"2024-08-05","cited_by_count":7,"area":"lr"},{"id":"2502.07443","title":"Approximating Human Strategic Reasoning with LLM-Enhanced Recursive Reasoners Leveraging Multi-agent Hypergames","created":"2025-02-11","cited_by_count":7,"area":"lr"},{"id":"2504.14773","title":"PLANET: A Collection of Benchmarks for Evaluating LLMs' Planning Capabilities","created":"2025-04-21","cited_by_count":7,"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":"2506.02387","title":"VS-Bench: Evaluating VLMs for Strategic Abilities in Multi-Agent Environments","created":"2025-06-03","cited_by_count":6,"area":"mllm"},{"id":"2602.10480","title":"Neuro-Symbolic Synergy for World Modeling","created":"2026-02-11","cited_by_count":6,"area":"wm"},{"id":"2605.24539","title":"DemoEvolve: Overcoming Sparse Feedback in Agentic Harness Evolution with Demonstrations","created":"2026-05-23","cited_by_count":6,"area":"agents"},{"id":"2407.06112","title":"Enhancing Language Model Rationality with Bi-Directional Deliberation Reasoning","created":"2024-07-08","cited_by_count":5,"area":"lr"},{"id":"2408.16081","title":"Towards Logically Sound Natural Language Reasoning with Logic-Enhanced Language Model Agents","created":"2024-08-28","cited_by_count":5,"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":"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":"2602.12316","title":"GT-HarmBench: Benchmarking AI Safety Risks Through the Lens of Game Theory","created":"2026-02-12","cited_by_count":5,"area":null},{"id":"2409.10372","title":"Integrated Design and Governance of Agentic AI Systems through Adaptive Information Modulation","created":"2024-09-16","cited_by_count":4,"area":"agents"},{"id":"2503.06709","title":"Delusions of Large Language Models","created":"2025-03-09","cited_by_count":4,"area":null},{"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":"2407.04467","title":"Are Large Language Models Strategic Decision Makers? A Study of Performance and Bias in Two-Player Non-Zero-Sum Games","created":"2024-07-05","cited_by_count":3,"area":null},{"id":"2410.14890","title":"Reasoning, Memorization, and Fine-Tuning Language Models for Non-Cooperative Games","created":"2024-10-18","cited_by_count":3,"area":"lr"},{"id":"2505.09396","title":"The Influence of Human-inspired Agentic Sophistication in LLM-driven Strategic Reasoners","created":"2025-05-14","cited_by_count":3,"area":"lr"},{"id":"2505.18597","title":"LLMs for Supply Chain Management","created":"2025-05-24","cited_by_count":3,"area":null},{"id":"2507.05707","title":"Agentic-R1: Distilled Dual-Strategy Reasoning","created":"2025-07-08","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":"2601.15047","title":"Game-Theoretic Lens on LLM-based Multi-Agent Systems","created":"2026-01-21","cited_by_count":3,"area":"lr"},{"id":"2602.07804","title":"Pruning as a Cooperative Game: Surrogate-Assisted Layer Contribution Estimation for Large Language Models","created":"2026-02-08","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":"2410.17820","title":"Understanding When Tree of Thoughts Succeeds: Larger Models Excel in Generation, Not Discrimination","created":"2024-10-23","cited_by_count":2,"area":"lr"},{"id":"2502.12825","title":"Reasoning and the Trusting Behavior of DeepSeek and GPT: An Experiment Revealing Hidden Fault Lines in Large Language Models","created":"2025-02-18","cited_by_count":2,"area":"lr"},{"id":"2504.08590","title":"Playpen: An Environment for Exploring Learning Through Conversational Interaction","created":"2025-04-11","cited_by_count":2,"area":"alignment"},{"id":"2510.08872","title":"GTAlign: Game-Theoretic Alignment of LLM Assistants for Social Welfare","created":"2025-10-10","cited_by_count":2,"area":null},{"id":"2510.10813","title":"The Fragility of Strategic Thinking in Large Language Models","created":"2025-10-12","cited_by_count":2,"area":"lr"},{"id":"2601.16276","title":"GameTalk: Training LLMs for Strategic Conversation","created":"2026-01-22","cited_by_count":2,"area":null},{"id":"2603.19466","title":"ProactiveBench: Benchmarking Proactiveness in Multimodal Large Language Models","created":"2026-03-19","cited_by_count":2,"area":"mllm"},{"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":"2609.31473","title":"Game Arena: Strategic LLM Evaluation in Competitive Environments","created":"2026-09-25","cited_by_count":2,"area":null},{"id":"2502.06494","title":"GuideLLM: Exploring LLM-Guided Conversation with Applications in Autobiography Interviewing","created":"2025-02-10","cited_by_count":1,"area":null},{"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":"2507.09495","title":"GenAI-based Multi-Agent Reinforcement Learning towards Distributed Agent Intelligence: A Generative-RL Agent Perspective","created":"2025-07-13","cited_by_count":1,"area":null},{"id":"2508.06111","title":"SKATE, a Scalable Tournament Eval: Weaker LLMs differentiate between stronger ones using verifiable challenges","created":"2025-08-08","cited_by_count":1,"area":null},{"id":"2508.17825","title":"FAIRGAMER: Evaluating Social Biases in LLM-Based Video Game NPCs","created":"2025-08-25","cited_by_count":1,"area":null},{"id":"2508.18091","title":"Teaching LLMs to Think Mathematically: A Critical Study of Decision-Making via Optimization","created":"2025-08-25","cited_by_count":1,"area":"lr"},{"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":"2601.16823","title":"Disentangling generalization and memorization in large language models using chess","created":"2026-01-23","cited_by_count":1,"area":"lr"},{"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":"2603.18563","title":"Reasonably reasoning AI agents can avoid game-theoretic failures in zero-shot, provably","created":"2026-03-19","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":"2605.09027","title":"GAMBIT: A Three-Mode Benchmark for Adversarial Robustness in Multi-Agent LLM Collectives","created":"2026-05-09","cited_by_count":1,"area":"agents"},{"id":"2605.29062","title":"Bosses, Kings, and the Commons: Cooperation Under Power Asymmetry in LLM Societies","created":"2026-05-27","cited_by_count":1,"area":null},{"id":"2605.31445","title":"Used Car Salesbots? Honesty and Credulity of LLMs as Bargaining Agents under Partial Information","created":"2026-05-29","cited_by_count":1,"area":"agents"},{"id":"2606.03544","title":"SAGE: A Quantitative Evaluation of Socialized Evolution in Agent Ecosystems","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2606.24162","title":"BehaviorBench: Benchmarking Foundation Models for Behavioral Science Tasks","created":"2026-06-23","cited_by_count":1,"area":null},{"id":"2606.27757","title":"Towards Reliable and Robust LLM Planning: Symbolic Feedback-Driven Iterative Self-Refinement Framework","created":"2026-06-26","cited_by_count":1,"area":null},{"id":"2608.25832","title":"Skill Issue: Are Skills Language-Invariant in LLMs?","created":"2026-08-26","cited_by_count":1,"area":null},{"id":"2406.14051","title":"How Many Parameters Does it Take to Change a Light Bulb? Evaluating Performance in Self-Play of Conversational Games as a Function of Model Characteristics","created":"2024-06-20","cited_by_count":0,"area":"synth"},{"id":"2503.04828","title":"Beyond Next Word Prediction: Developing Comprehensive Evaluation Frameworks for measuring LLM performance on real world applications","created":"2025-03-05","cited_by_count":0,"area":null},{"id":"2503.10229","title":"R.U.Psycho? Robust Unified Psychometric Testing of Language Models","created":"2025-03-13","cited_by_count":0,"area":null}],"next_cursor":"100"}