{"total":79,"rows":[{"id":"2509.02544","title":"UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning","created":"2025-09-02","cited_by_count":215,"area":"lr"},{"id":"2403.03186","title":"Cradle: Empowering Foundation Agents Towards General Computer Control","created":"2024-03-05","cited_by_count":117,"area":null},{"id":"2407.06567","title":"FinCon: A Synthesized LLM Multi-Agent System with Conceptual Verbal Reinforcement for Enhanced Financial Decision Making","created":"2024-07-09","cited_by_count":113,"area":"agents"},{"id":"2404.02039","title":"A Survey on Large Language Model-Based Game Agents","created":"2024-04-02","cited_by_count":112,"area":"agents"},{"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":"2402.17574","title":"Agent-Pro: Learning to Evolve via Policy-Level Reflection and Optimization","created":"2024-02-27","cited_by_count":94,"area":"wm"},{"id":"2404.15676","title":"Beyond Chain-of-Thought: A Survey of Chain-of-X Paradigms for LLMs","created":"2024-04-24","cited_by_count":48,"area":"lr"},{"id":"2405.10313","title":"How Far Are We From AGI: Are LLMs All We Need?","created":"2024-05-16","cited_by_count":31,"area":null},{"id":"2410.07927","title":"Efficient Reinforcement Learning with Large Language Model Priors","created":"2024-10-10","cited_by_count":30,"area":null},{"id":"2402.01118","title":"PokeLLMon: A Human-Parity Agent for Pokemon Battles with Large Language Models","created":"2024-02-02","cited_by_count":26,"area":"agents"},{"id":"2408.15971","title":"BattleAgentBench: A Benchmark for Evaluating Cooperation and Competition Capabilities of Language Models in Multi-Agent Systems","created":"2024-08-28","cited_by_count":26,"area":"agents"},{"id":"2403.08282","title":"Hierarchical Auto-Organizing System for Open-Ended Multi-Agent Navigation","created":"2024-03-13","cited_by_count":24,"area":"agents"},{"id":"2405.19946","title":"Learning to Discuss Strategically: A Case Study on One Night Ultimate Werewolf","created":"2024-05-30","cited_by_count":24,"area":null},{"id":"2403.02613","title":"Large Language Models and Video Games: A Preliminary Scoping Review","created":"2024-03-05","cited_by_count":23,"area":null},{"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":"2403.10249","title":"A Survey on Game Playing Agents and Large Models: Methods, Applications, and Challenges","created":"2024-03-15","cited_by_count":22,"area":null},{"id":"2412.01800","title":"PhysGame: Uncovering Physical Commonsense Violations in Gameplay Videos","created":"2024-12-02","cited_by_count":22,"area":null},{"id":"2507.15815","title":"LLM Economist: Large Population Models and Mechanism Design in Multi-Agent Generative Simulacra","created":"2025-07-21","cited_by_count":22,"area":"agents"},{"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":"2404.04619","title":"Do We Really Need a Complex Agent System? Distill Embodied Agent into a Single Model","created":"2024-04-06","cited_by_count":19,"area":"agents"},{"id":"2405.18092","title":"LLM experiments with simulation: Large Language Model Multi-Agent System for Simulation Model Parametrization in Digital Twins","created":"2024-05-28","cited_by_count":16,"area":"agents"},{"id":"2503.04094","title":"Pok\\'eChamp: an Expert-level Minimax Language Agent","created":"2025-03-06","cited_by_count":16,"area":"agents"},{"id":"2502.04686","title":"Learning Strategic Language Agents in the Werewolf Game with Iterative Latent Space Policy Optimization","created":"2025-02-07","cited_by_count":15,"area":"agents"},{"id":"2505.02156","title":"Adaptive Social Learning via Mode Policy Optimization for Language Agents","created":"2025-05-04","cited_by_count":15,"area":"lr"},{"id":"2407.15295","title":"VideoGameBunny: Towards vision assistants for video games","created":"2024-07-21","cited_by_count":11,"area":"mllm"},{"id":"2602.11583","title":"The Five Ws of Multi-Agent Communication: Who Talks to Whom, When, What, and Why -- A Survey from MARL to Emergent Language and LLMs","created":"2026-02-12","cited_by_count":10,"area":"agents"},{"id":"2410.03997","title":"YOLO-MARL: You Only LLM Once for Multi-Agent Reinforcement Learning","created":"2024-10-05","cited_by_count":9,"area":"agents"},{"id":"2503.13356","title":"Agents Play Thousands of 3D Video Games","created":"2025-03-17","cited_by_count":9,"area":"agents"},{"id":"2505.19481","title":"Win Fast or Lose Slow: Balancing Speed and Accuracy in Latency-Sensitive Decisions of LLMs","created":"2025-05-26","cited_by_count":9,"area":"agents"},{"id":"2508.19506","title":"Learning Game-Playing Agents with Generative Code Optimization","created":"2025-08-27","cited_by_count":8,"area":"agents"},{"id":"2403.05468","title":"Will GPT-4 Run DOOM?","created":"2024-03-08","cited_by_count":6,"area":null},{"id":"2410.16024","title":"SMAC-R1: The Emergence of Intelligence in Decision-Making Tasks","created":"2024-10-21","cited_by_count":6,"area":null},{"id":"2407.06112","title":"Enhancing Language Model Rationality with Bi-Directional Deliberation Reasoning","created":"2024-07-08","cited_by_count":5,"area":"lr"},{"id":"2410.02829","title":"LLMs May Not Be Human-Level Players, But They Can Be Testers: Measuring Game Difficulty with LLM Agents","created":"2024-10-01","cited_by_count":5,"area":"agents"},{"id":"2503.05383","title":"AVA: Attentive VLM Agent for Mastering StarCraft II","created":"2025-03-07","cited_by_count":5,"area":"mllm"},{"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":"2401.06792","title":"LightHouse: A Survey of AGI Hallucination","created":"2024-01-08","cited_by_count":4,"area":null},{"id":"2503.23875","title":"GenSwarm: Scalable Multi-Robot Code-Policy Generation and Deployment via Language Models","created":"2025-03-31","cited_by_count":4,"area":null},{"id":"2601.05899","title":"TowerMind: A Tower Defence Game Learning Environment and Benchmark for LLM as Agents","created":"2026-01-09","cited_by_count":4,"area":"agents"},{"id":"2508.09586","title":"EvoCurr: Self-evolving Curriculum with Behavior Code Generation for Complex Decision-making","created":"2025-08-13","cited_by_count":3,"area":"synth"},{"id":"2508.10428","title":"SC2Arena and StarEvolve: Benchmark and Self-Improvement Framework for LLMs in Complex Decision-Making Tasks","created":"2025-08-14","cited_by_count":3,"area":"synth"},{"id":"2508.16580","title":"Adaptive Command: Real-Time Policy Adjustment via Language Models in StarCraft II","created":"2025-08-05","cited_by_count":3,"area":null},{"id":"2509.01052","title":"FlashAdventure: A Benchmark for GUI Agents Solving Full Story Arcs in Diverse Adventure Games","created":"2025-09-01","cited_by_count":3,"area":"agents"},{"id":"2510.09087","title":"The Stackelberg Speaker: Optimizing Persuasive Communication in Social Deduction Games","created":"2025-10-10","cited_by_count":3,"area":null},{"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":"2411.09176","title":"Gazing at Rewards: Eye Movements as a Lens into Human and AI Decision-Making in Hybrid Visual Foraging","created":"2024-11-14","cited_by_count":2,"area":null},{"id":"2412.11417","title":"RL-LLM-DT: An Automatic Decision Tree Generation Method Based on RL Evaluation and LLM Enhancement","created":"2024-12-16","cited_by_count":2,"area":null},{"id":"2502.10148","title":"Closed-Loop Vision-Language Planning for Multi-Agent Coordination","created":"2025-02-14","cited_by_count":2,"area":"agents"},{"id":"2505.08459","title":"Strategy-Augmented Planning for Large Language Models via Opponent Exploitation","created":"2025-05-13","cited_by_count":2,"area":null},{"id":"2505.23191","title":"ExpeTrans: LLMs Are Experiential Transfer Learners","created":"2025-05-29","cited_by_count":2,"area":null},{"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":"2510.18395","title":"Memory-Augmented State Machine Prompting: A Novel LLM Agent Framework for Real-Time Strategy Games","created":"2025-10-21","cited_by_count":2,"area":"agents"},{"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":"2409.18989","title":"SC-Phi2: A Fine-tuned Small Language Model for StarCraft II Macromanagement Tasks","created":"2024-09-17","cited_by_count":1,"area":null},{"id":"2503.21263","title":"Cultivating Game Sense for Yourself: Making VLMs Gaming Experts","created":"2025-03-27","cited_by_count":1,"area":null},{"id":"2505.17512","title":"Is Your LLM Really Mastering the Concept? A Multi-Agent Benchmark","created":"2025-05-23","cited_by_count":1,"area":"agents"},{"id":"2507.05638","title":"LLMs are Introvert","created":"2025-07-08","cited_by_count":1,"area":null},{"id":"2601.16471","title":"Order from Chaos: Physical World Understanding from Glitchy Gameplay Videos","created":"2026-01-23","cited_by_count":1,"area":null},{"id":"2602.13222","title":"Computability of Agentic Systems","created":"2026-01-26","cited_by_count":1,"area":"agents"},{"id":"2603.21280","title":"WARBENCH: A Comprehensive Benchmark for Evaluating LLMs in Military Decision-Making","created":"2026-03-22","cited_by_count":1,"area":null},{"id":"2502.16402","title":"Navigation-GPT: A Robust and Adaptive Framework Utilizing Large Language Models for Navigation Applications","created":"2025-02-23","cited_by_count":0,"area":null},{"id":"2507.02002","title":"Dynamic Strategy Adaptation in Multi-Agent Environments with Large Language Models","created":"2025-07-01","cited_by_count":0,"area":"lr"},{"id":"2509.13127","title":"Empowering LLMs with Parameterized Skills for Adversarial Long-Horizon Planning","created":"2025-09-16","cited_by_count":0,"area":null},{"id":"2509.26340","title":"Memory-Driven Self-Improvement for Decision Making with Large Language Models","created":"2025-09-30","cited_by_count":0,"area":"synth"},{"id":"2511.22598","title":"LLM-Cave: A benchmark and light environment for large language models reasoning and decision-making system","created":"2025-11-27","cited_by_count":0,"area":"lr"},{"id":"2512.08743","title":"Single-Agent Scaling Fails Multi-Agent Intelligence: Towards Foundation Models with Native Multi-Agent Intelligence","created":"2025-12-09","cited_by_count":0,"area":"agents"},{"id":"2602.14857","title":"World Models for Policy Refinement in StarCraft II","created":"2026-02-16","cited_by_count":0,"area":"wm"},{"id":"2603.23875","title":"Self-Evolving Multi-Agent Framework for Efficient Decision Making in Real-Time Strategy Scenarios","created":"2026-03-25","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":"2606.04202","title":"SMAC-Talk: A Natural Language Extension of the StarCraft Multi-Agent Challenge for Large Language Models","created":"2026-06-02","cited_by_count":0,"area":"agents"},{"id":"2606.23668","title":"On the Limits of Prompt-Conditioned Language Models as General-Purpose Learners","created":"2026-06-22","cited_by_count":0,"area":null},{"id":"2606.26787","title":"AIGP: An LLM-Based Framework for Long-Term Value Alignment in E-Commerce Pricing","created":"2026-06-25","cited_by_count":0,"area":"alignment"},{"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":"2606.29932","title":"SAGA: Scene-Aware, Goal-Evolving Agents for Long-Horizon Strategy Game Planning","created":"2026-06-29","cited_by_count":0,"area":"agents"},{"id":"2608.12626","title":"LLMs Are Not Good Strategists, Yet Memory-Enhanced Agency Boosts Reasoning","created":"2026-08-12","cited_by_count":0,"area":"lr"},{"id":"2609.18996","title":"Compiled Agency: Frontier General-Purpose Coding Agents Build Winning Game Players from Bare Interaction - from Flappy Bird to StarCraft II and Civilization","created":"2026-07-17","cited_by_count":0,"area":"agents"},{"id":"2609.35427","title":"LLMs are General Asynchronous Agents","created":"2026-09-28","cited_by_count":0,"area":"agents"}],"next_cursor":null}