{"list":"other","total":135,"rows":[{"id":"1509.02971","title":"Continuous control with deep reinforcement learning","created":"2015-09-09","cited_by_count":3407},{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"1502.05477","title":"Trust Region Policy Optimization","created":"2015-02-19","cited_by_count":2580},{"id":"2204.01691","title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","created":"2022-04-04","cited_by_count":2348},{"id":"2305.16291","title":"Voyager: An Open-Ended Embodied Agent with Large Language Models","created":"2023-05-25","cited_by_count":2191},{"id":"2308.08155","title":"AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation","created":"2023-08-16","cited_by_count":1988},{"id":"2305.14325","title":"Improving Factuality and Reasoning in Language Models through Multiagent Debate","created":"2023-05-23","cited_by_count":1784},{"id":"1509.06461","title":"Deep Reinforcement Learning with Double Q-learning","created":"2015-09-22","cited_by_count":1745},{"id":"1706.02275","title":"Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments","created":"2017-06-07","cited_by_count":1558},{"id":"1912.06680","title":"Dota 2 with Large Scale Deep Reinforcement Learning","created":"2019-12-13","cited_by_count":1103},{"id":"2305.19118","title":"Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate","created":"2023-05-30","cited_by_count":1011},{"id":"2307.07924","title":"ChatDev: Communicative Agents for Software Development","created":"2023-07-16","cited_by_count":919},{"id":"1712.01815","title":"Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm","created":"2017-12-05","cited_by_count":734},{"id":"2503.13657","title":"Why Do Multi-Agent LLM Systems Fail?","created":"2025-03-17","cited_by_count":604},{"id":"1902.04043","title":"The StarCraft Multi-Agent Challenge","created":"2019-02-11","cited_by_count":597},{"id":"2306.02561","title":"LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion","created":"2023-06-05","cited_by_count":564},{"id":"2501.04227","title":"Agent Laboratory: Using LLM Agents as Research Assistants","created":"2025-01-08","cited_by_count":425},{"id":"1610.00633","title":"Deep Reinforcement Learning for Robotic Manipulation with Asynchronous Off-Policy Updates","created":"2016-10-03","cited_by_count":353},{"id":"2311.10537","title":"MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoning","created":"2023-11-16","cited_by_count":316},{"id":"2309.13007","title":"ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMs","created":"2023-09-22","cited_by_count":309},{"id":"2305.17144","title":"Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memory","created":"2023-05-25","cited_by_count":289},{"id":"2008.01062","title":"QPLEX: Duplex Dueling Multi-Agent Q-Learning","created":"2020-08-03","cited_by_count":270},{"id":"2309.04658","title":"Exploring Large Language Models for Communication Games: An Empirical Study on Werewolf","created":"2023-09-09","cited_by_count":241},{"id":"2310.02124","title":"Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology View","created":"2023-10-03","cited_by_count":222},{"id":"2405.02957","title":"Agent Hospital: A Simulacrum of Hospital with Evolvable Medical Agents","created":"2024-05-05","cited_by_count":218},{"id":"2404.18231","title":"From Persona to Personalization: A Survey on Role-Playing Language Agents","created":"2024-04-28","cited_by_count":212},{"id":"1702.03037","title":"Multi-agent Reinforcement Learning in Sequential Social Dilemmas","created":"2017-02-10","cited_by_count":209},{"id":"1810.11187","title":"TarMAC: Targeted Multi-Agent Communication","created":"2018-10-26","cited_by_count":208},{"id":"1612.07182","title":"Multi-Agent Cooperation and the Emergence of (Natural) Language","created":"2016-12-21","cited_by_count":185},{"id":"2405.11403","title":"MapCoder: Multi-Agent Code Generation for Competitive Problem Solving","created":"2024-05-18","cited_by_count":177},{"id":"2006.02419","title":"Emergent Multi-Agent Communication in the Deep Learning Era","created":"2020-06-03","cited_by_count":170},{"id":"2401.03568","title":"Agent AI: Surveying the Horizons of Multimodal Interaction","created":"2024-01-07","cited_by_count":170},{"id":"2402.18013","title":"A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systems","created":"2024-02-28","cited_by_count":170},{"id":"1810.09202","title":"Graph Convolutional Reinforcement Learning","created":"2018-10-22","cited_by_count":152},{"id":"2310.18940","title":"Language Agents with Reinforcement Learning for Strategic Play in the Werewolf Game","created":"2023-10-29","cited_by_count":152},{"id":"2311.17227","title":"War and Peace (WarAgent): Large Language Model-based Multi-Agent Simulation of World Wars","created":"2023-11-28","cited_by_count":145},{"id":"2211.09110","title":"Holistic Evaluation of Language Models","created":"2022-11-16","cited_by_count":131},{"id":"2404.02039","title":"A Survey on Large Language Model-Based Game Agents","created":"2024-04-02","cited_by_count":112},{"id":"2203.08975","title":"A Survey of Multi-Agent Deep Reinforcement Learning with Communication","created":"2022-03-16","cited_by_count":104},{"id":"2310.01320","title":"Avalon's Game of Thoughts: Battle Against Deception through Recursive Contemplation","created":"2023-10-02","cited_by_count":104},{"id":"2401.04259","title":"MARG: Multi-Agent Review Generation for Scientific Papers","created":"2024-01-08","cited_by_count":104},{"id":"2305.11595","title":"Examining Inter-Consistency of Large Language Models Collaboration: An In-depth Analysis via Debate","created":"2023-05-19","cited_by_count":97},{"id":"1703.10069","title":"Multiagent Bidirectionally-Coordinated Nets: Emergence of Human-level Coordination in Learning to Play StarCraft Combat Games","created":"2017-03-29","cited_by_count":96},{"id":"1609.05521","title":"Playing FPS Games with Deep Reinforcement Learning","created":"2016-09-18","cited_by_count":95},{"id":"2409.05556","title":"SciAgents: Automating scientific discovery through multi-agent intelligent graph reasoning","created":"2024-09-09","cited_by_count":94},{"id":"1902.01554","title":"Learning to Schedule Communication in Multi-agent Reinforcement Learning","created":"2019-02-05","cited_by_count":93},{"id":"2309.09971","title":"MindAgent: Emergent Gaming Interaction","created":"2023-09-18","cited_by_count":88},{"id":"1910.05366","title":"Learning Nearly Decomposable Value Functions Via Communication Minimization","created":"2019-10-11","cited_by_count":86},{"id":"2404.02183","title":"Self-Organized Agents: A LLM Multi-Agent Framework toward Ultra Large-Scale Code Generation and Optimization","created":"2024-04-02","cited_by_count":84},{"id":"2312.01823","title":"Exchange-of-Thought: Enhancing Large Language Model Capabilities through Cross-Model Communication","created":"2023-12-04","cited_by_count":82},{"id":"2411.00081","title":"PARTNR: A Benchmark for Planning and Reasoning in Embodied Multi-agent Tasks","created":"2024-10-31","cited_by_count":82},{"id":"2401.05268","title":"AutoAct: Automatic Agent Learning from Scratch for QA via Self-Planning","created":"2024-01-10","cited_by_count":81},{"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},{"id":"2002.01365","title":"Compositional Languages Emerge in a Neural Iterated Learning Model","created":"2020-02-04","cited_by_count":75},{"id":"2405.11106","title":"LLM-based Multi-Agent Reinforcement Learning: Current and Future Directions","created":"2024-05-17","cited_by_count":67},{"id":"2310.14985","title":"LLM-Based Agent Society Investigation: Collaboration and Confrontation in Avalon Gameplay","created":"2023-10-23","cited_by_count":63},{"id":"1804.03980","title":"Emergent Communication through Negotiation","created":"2018-04-11","cited_by_count":62},{"id":"2109.06275","title":"MindCraft: Theory of Mind Modeling for Situated Dialogue in Collaborative Tasks","created":"2021-09-13","cited_by_count":62},{"id":"2006.11438","title":"Deep Implicit Coordination Graphs for Multi-agent Reinforcement Learning","created":"2020-06-19","cited_by_count":60},{"id":"1909.04499","title":"Countering Language Drift via Visual Grounding","created":"2019-09-10","cited_by_count":55},{"id":"2004.01339","title":"Multi-agent Reinforcement Learning for Networked System Control","created":"2020-04-03","cited_by_count":53},{"id":"2411.00114","title":"Project Sid: Many-agent simulations toward AI civilization","created":"2024-10-31","cited_by_count":49},{"id":"2310.05036","title":"AvalonBench: Evaluating LLMs Playing the Game of Avalon","created":"2023-10-08","cited_by_count":47},{"id":"2407.13943","title":"Werewolf Arena: A Case Study in LLM Evaluation via Social Deduction","created":"2024-07-18","cited_by_count":45},{"id":"1907.00852","title":"EGG: a toolkit for research on Emergence of lanGuage in Games","created":"2019-07-01","cited_by_count":42},{"id":"2308.12503","title":"CGMI: Configurable General Multi-Agent Interaction Framework","created":"2023-08-24","cited_by_count":42},{"id":"2211.13746","title":"Melting Pot 2.0","created":"2022-11-24","cited_by_count":40},{"id":"1901.08706","title":"Emergent Linguistic Phenomena in Multi-Agent Communication Games","created":"2019-01-25","cited_by_count":36},{"id":"2402.16499","title":"LLMArena: Assessing Capabilities of Large Language Models in Dynamic Multi-Agent Environments","created":"2024-02-26","cited_by_count":36},{"id":"2406.05720","title":"VillagerAgent: A Graph-Based Multi-Agent Framework for Coordinating Complex Task Dependencies in Minecraft","created":"2024-06-09","cited_by_count":35},{"id":"1511.03791","title":"Towards Vision-Based Deep Reinforcement Learning for Robotic Motion Control","created":"2015-11-12","cited_by_count":33},{"id":"1804.02341","title":"Compositional Obverter Communication Learning From Raw Visual Input","created":"2018-04-06","cited_by_count":30},{"id":"1910.11424","title":"Capacity, Bandwidth, and Compositionality in Emergent Language Learning","created":"2019-10-24","cited_by_count":30},{"id":"2312.00746","title":"Deciphering Digital Detectives: Understanding LLM Behaviors and Capabilities in Multi-Agent Mystery Games","created":"2023-12-01","cited_by_count":30},{"id":"2506.08292","title":"From Debate to Equilibrium: Belief-Driven Multi-Agent LLM Reasoning via Bayesian Nash Equilibrium","created":"2025-06-09","cited_by_count":26},{"id":"2405.15145","title":"CulturePark: Boosting Cross-cultural Understanding in Large Language Models","created":"2024-05-24","cited_by_count":24},{"id":"1710.06922","title":"Emergent Translation in Multi-Agent Communication","created":"2017-10-12","cited_by_count":22},{"id":"1602.02672","title":"Learning to Communicate to Solve Riddles with Deep Distributed Recurrent Q-Networks","created":"2016-02-08","cited_by_count":21},{"id":"2410.05130","title":"Scalable and Accurate Graph Reasoning with LLM-based Multi-Agents","created":"2024-10-07","cited_by_count":21},{"id":"2103.08067","title":"Quasi-Equivalence Discovery for Zero-Shot Emergent Communication","created":"2021-03-14","cited_by_count":19},{"id":"2203.13344","title":"Linking Emergent and Natural Languages via Corpus Transfer","created":"2022-03-24","cited_by_count":19},{"id":"1809.00549","title":"Emergence of Communication in an Interactive World with Consistent Speakers","created":"2018-09-03","cited_by_count":18},{"id":"1901.01536","title":"Exploring applications of deep reinforcement learning for real-world autonomous driving systems","created":"2019-01-06","cited_by_count":18},{"id":"2010.15896","title":"Exploring Zero-Shot Emergent Communication in Embodied Multi-Agent Populations","created":"2020-10-29","cited_by_count":18},{"id":"2403.19267","title":"MineLand: Simulating Large-Scale Multi-Agent Interactions with Limited Multimodal Senses and Physical Needs","created":"2024-03-28","cited_by_count":18},{"id":"2004.03420","title":"Emergent Language Generalization and Acquisition Speed are not tied to Compositionality","created":"2020-04-07","cited_by_count":17},{"id":"2407.03302","title":"A Review of the Applications of Deep Learning-Based Emergent Communication","created":"2024-07-03","cited_by_count":17},{"id":"1611.03218","title":"Learning to Play Guess Who? and Inventing a Grounded Language as a Consequence","created":"2016-11-10","cited_by_count":15},{"id":"2407.16252","title":"LawLuo: A Multi-Agent Collaborative Framework for Multi-Round Chinese Legal Consultation","created":"2024-07-23","cited_by_count":14},{"id":"1811.12557","title":"Deep Multi-Agent Reinforcement Learning with Relevance Graphs","created":"2018-11-30","cited_by_count":13},{"id":"2004.02780","title":"Networked Multi-Agent Reinforcement Learning with Emergent Communication","created":"2020-04-06","cited_by_count":13},{"id":"2404.01602","title":"Helmsman of the Masses? Evaluate the Opinion Leadership of Large Language Models in the Werewolf Game","created":"2024-04-02","cited_by_count":13},{"id":"2409.02645","title":"Emergent Language: A Survey and Taxonomy","created":"2024-09-04","cited_by_count":13},{"id":"2502.11518","title":"Generative Multi-Agent Collaboration in Embodied AI: A Systematic Review","created":"2025-02-17","cited_by_count":13},{"id":"1712.07305","title":"Revisiting the Master-Slave Architecture in Multi-Agent Deep Reinforcement Learning","created":"2017-12-20","cited_by_count":12},{"id":"2311.05720","title":"Long-Horizon Dialogue Understanding for Role Identification in the Game of Avalon with Large Language Models","created":"2023-11-09","cited_by_count":12},{"id":"1905.11871","title":"Miss Tools and Mr Fruit: Emergent communication in agents learning about object affordances","created":"2019-05-28","cited_by_count":11},{"id":"2012.09486","title":"ReferentialGym: A Nomenclature and Framework for Language Emergence & Grounding in (Visual) Referential Games","created":"2020-12-17","cited_by_count":11},{"id":"2012.10776","title":"On (Emergent) Systematic Generalisation and Compositionality in Visual Referential Games with Straight-Through Gumbel-Softmax Estimator","created":"2020-12-19","cited_by_count":11},{"id":"2106.03982","title":"Expressivity of Emergent Language is a Trade-off between Contextual Complexity and Unpredictability","created":"2021-06-07","cited_by_count":11}],"next_cursor":"100"}