{"total":42,"rows":[{"id":"2305.16291","title":"Voyager: An Open-Ended Embodied Agent with Large Language Models","created":"2023-05-25","cited_by_count":2191,"area":"agents"},{"id":"2304.08354","title":"Tool Learning with Foundation Models","created":"2023-04-17","cited_by_count":302,"area":"agents"},{"id":"2310.18940","title":"Language Agents with Reinforcement Learning for Strategic Play in the Werewolf Game","created":"2023-10-29","cited_by_count":152,"area":"agents"},{"id":"2503.23037","title":"Agentic Large Language Models, a survey","created":"2025-03-29","cited_by_count":108,"area":"agents"},{"id":"2312.11865","title":"Large Language Models Play StarCraft II: Benchmarks and A Chain of Summarization Approach","created":"2023-12-19","cited_by_count":79,"area":"agents"},{"id":"2508.04652","title":"LLM Collaboration With Multi-Agent Reinforcement Learning","created":"2025-08-06","cited_by_count":49,"area":"agents"},{"id":"2310.08067","title":"GameGPT: Multi-agent Collaborative Framework for Game Development","created":"2023-10-12","cited_by_count":43,"area":"agents"},{"id":"2502.14074","title":"Investigating Non-Transitivity in LLM-as-a-Judge","created":"2025-02-19","cited_by_count":34,"area":"agents"},{"id":"2309.14365","title":"An In-depth Survey of Large Language Model-based Artificial Intelligence Agents","created":"2023-09-23","cited_by_count":31,"area":"agents"},{"id":"2512.04797","title":"SIMA 2: A Generalist Embodied Agent for Virtual Worlds","created":"2025-12-04","cited_by_count":31,"area":"agents"},{"id":"2601.02427","title":"NitroGen: An Open Foundation Model for Generalist Gaming Agents","created":"2026-01-04","cited_by_count":27,"area":"agents"},{"id":"2312.17653","title":"LARP: Language-Agent Role Play for Open-World Games","created":"2023-12-24","cited_by_count":24,"area":"agents"},{"id":"2607.13104","title":"Self-Improvements in Modern Agentic Systems: A Survey","created":"2026-07-14","cited_by_count":19,"area":"agents"},{"id":"2502.05453","title":"LLM-Powered Decentralized Generative Agents with Adaptive Hierarchical Knowledge Graph for Cooperative Planning","created":"2025-02-08","cited_by_count":18,"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":"2604.20987","title":"Co-Evolving LLM Decision and Skill Bank Agents for Long-Horizon Tasks","created":"2026-04-22","cited_by_count":15,"area":"agents"},{"id":"2601.01743","title":"AI Agent Systems: Architectures, Applications, and Evaluation","created":"2026-01-05","cited_by_count":13,"area":"agents"},{"id":"2501.14225","title":"Multi-agent KTO: Reinforcing Strategic Interactions of Large Language Model in Language Game","created":"2025-01-24","cited_by_count":10,"area":"agents"},{"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":"2503.13356","title":"Agents Play Thousands of 3D Video Games","created":"2025-03-17","cited_by_count":9,"area":"agents"},{"id":"2401.00006","title":"Building Open-Ended Embodied Agent via Language-Policy Bidirectional Adaptation","created":"2023-12-12","cited_by_count":6,"area":"agents"},{"id":"2608.12253","title":"One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL","created":"2026-08-12","cited_by_count":6,"area":"agents"},{"id":"2601.08237","title":"The End of Reward Engineering: How LLMs Are Redefining Multi-Agent Coordination","created":"2026-01-13","cited_by_count":3,"area":"agents"},{"id":"2602.05327","title":"ProAct: Agentic Lookahead in Interactive Environments","created":"2026-02-05","cited_by_count":3,"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":"2402.05829","title":"Limitations of Agents Simulated by Predictive Models","created":"2024-02-08","cited_by_count":1,"area":"agents"},{"id":"2411.19547","title":"Training Agents with Weakly Supervised Feedback from Large Language Models","created":"2024-11-29","cited_by_count":1,"area":"agents"},{"id":"2506.17539","title":"Breaking Single-Tester Limits: Multi-Agent LLMs for Multi-User Feature Testing","created":"2025-06-21","cited_by_count":1,"area":"agents"},{"id":"2509.14547","title":"(P)rior(D)yna(F)low: A Priori Dynamic Workflow Construction via Multi-Agent Collaboration","created":"2025-09-18","cited_by_count":1,"area":"agents"},{"id":"2510.03405","title":"LegalSim: Multi-Agent Simulation of Legal Systems for Discovering Procedural Exploits","created":"2025-10-03","cited_by_count":1,"area":"agents"},{"id":"2605.23652","title":"One Policy, Infinite NPCs: Persona-Traceable Shared RL Policies for Scalable Game Agents","created":"2026-05-22","cited_by_count":1,"area":"agents"},{"id":"2505.15306","title":"Multiple Weaks Win Single Strong: Large Language Models Ensemble Weak Reinforcement Learning Agents into a Supreme One","created":"2025-05-21","cited_by_count":0,"area":"agents"},{"id":"2512.11270","title":"A-LAMP: Agentic LLM-Based Framework for Automated MDP Modeling and Policy Generation","created":"2025-12-12","cited_by_count":0,"area":"agents"},{"id":"2602.06232","title":"RuleSmith: Multi-Agent LLMs for Automated Game Balancing","created":"2026-02-05","cited_by_count":0,"area":"agents"},{"id":"2605.17885","title":"Multi-agent AI systems outperform human teams in creativity","created":"2026-05-18","cited_by_count":0,"area":"agents"},{"id":"2607.06854","title":"A Gold-Standard Study of What Makes a Lightweight Game-Playing Agent Strong","created":"2026-07-07","cited_by_count":0,"area":"agents"},{"id":"2609.02931","title":"LLM-Guided Reinforcement Learning for Adaptive NPC Behavior in Multi-Agent Combat Games","created":"2026-08-27","cited_by_count":0,"area":"agents"},{"id":"2609.04217","title":"At Equal Inference Cost, Multi-Agent Structure Does Not Beat a Single Frozen Agent","created":"2026-06-25","cited_by_count":0,"area":"agents"},{"id":"2609.24025","title":"Synthesizing Reactive Character Behaviors for Continuous Games via Programmatic Policy Search","created":"2026-09-21","cited_by_count":0,"area":"agents"},{"id":"2609.38881","title":"STRATA: Self-Learning Through Role-Aligned Tiered Agents for Real-Time Strategy Games","created":"2026-09-30","cited_by_count":0,"area":"agents"},{"id":"2610.08076","title":"SpeedrunBench: Challenging LLM Agents with Video Game Speedrunning","created":"2026-10-06","cited_by_count":0,"area":"agents"}],"next_cursor":null}