{"total":101,"rows":[{"id":"2303.17760","title":"CAMEL: Communicative Agents for \"Mind\" Exploration of Large Language Model Society","created":"2023-03-31","cited_by_count":1395,"area":"agents"},{"id":"2310.11667","title":"SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents","created":"2023-10-18","cited_by_count":367,"area":"agents"},{"id":"2307.02485","title":"Building Cooperative Embodied Agents Modularly with Large Language Models","created":"2023-07-05","cited_by_count":237,"area":"agents"},{"id":"2401.03428","title":"Exploring Large Language Model based Intelligent Agents: Definitions, Methods, and Prospects","created":"2024-01-07","cited_by_count":132,"area":"agents"},{"id":"2403.12482","title":"Embodied LLM Agents Learn to Cooperate in Organized Teams","created":"2024-03-19","cited_by_count":82,"area":"agents"},{"id":"2405.11106","title":"LLM-based Multi-Agent Reinforcement Learning: Current and Future Directions","created":"2024-05-17","cited_by_count":67,"area":"agents"},{"id":"2504.16129","title":"MARFT: Multi-Agent Reinforcement Fine-Tuning","created":"2025-04-21","cited_by_count":52,"area":"agents"},{"id":"2311.13884","title":"Controlling Large Language Model-based Agents for Large-Scale Decision-Making: An Actor-Critic Approach","created":"2023-11-23","cited_by_count":38,"area":"agents"},{"id":"2502.14743","title":"Multi-Agent Coordination across Diverse Applications: A Survey","created":"2025-02-20","cited_by_count":37,"area":"agents"},{"id":"2509.17158","title":"ARE: Scaling Up Agent Environments and Evaluations","created":"2025-09-21","cited_by_count":30,"area":"agents"},{"id":"2511.12159","title":"CriticSearch: Fine-Grained Credit Assignment for Search Agents via a Retrospective Critic","created":"2025-11-15","cited_by_count":30,"area":"agents"},{"id":"2505.00753","title":"LLM-Based Human-Agent Collaboration and Interaction Systems: A Survey","created":"2025-05-01","cited_by_count":29,"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":"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":"2502.16863","title":"Leveraging Large Language Models for Effective and Explainable Multi-Agent Credit Assignment","created":"2025-02-24","cited_by_count":18,"area":"agents"},{"id":"2603.02604","title":"Heterogeneous Agent Collaborative Reinforcement Learning","created":"2026-03-03","cited_by_count":15,"area":"agents"},{"id":"2506.01538","title":"LAMARL: LLM-Aided Multi-Agent Reinforcement Learning for Cooperative Policy Generation","created":"2025-06-02","cited_by_count":13,"area":"agents"},{"id":"2511.02687","title":"The Collaboration Gap: Exploration and Benchmarking of Open-World Agentic Cooperation","created":"2025-11-04","cited_by_count":13,"area":"agents"},{"id":"2502.03723","title":"Speaking the Language of Teamwork: LLM-Guided Credit Assignment in Multi-Agent Reinforcement Learning","created":"2025-02-06","cited_by_count":10,"area":"agents"},{"id":"2506.01839","title":"Beyond Static Responses: Multi-Agent LLM Systems as a New Paradigm for Social Science Research","created":"2025-06-02","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":"2410.02511","title":"Stop Wandering, Find the Keys: LLMs Discriminate Key States for Efficient Multi-Agent Exploration","created":"2024-10-03","cited_by_count":9,"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":"2503.21807","title":"LERO: LLM-driven Evolutionary framework with Hybrid Rewards and Enhanced Observation for Multi-Agent Reinforcement Learning","created":"2025-03-25","cited_by_count":9,"area":"agents"},{"id":"2506.19846","title":"HiMA-Ecom: Enabling Joint Training of Hierarchical Multi-Agent E-commerce Assistants","created":"2025-06-24","cited_by_count":9,"area":"agents"},{"id":"2505.18397","title":"An Outlook on the Opportunities and Challenges of Multi-Agent AI Systems","created":"2025-05-23","cited_by_count":8,"area":"agents"},{"id":"2511.19368","title":"LLM-Driven Stationarity-Aware Expert Demonstrations for Multi-Agent Reinforcement Learning in Mobile Systems","created":"2025-11-24","cited_by_count":8,"area":"agents"},{"id":"2601.21972","title":"Learning Decentralized LLM Collaboration with Multi-Agent Actor Critic","created":"2026-01-29","cited_by_count":8,"area":"agents"},{"id":"2404.17780","title":"Verco: Learning Coordinated Verbal Communication for Multi-agent Reinforcement Learning","created":"2024-04-27","cited_by_count":7,"area":"agents"},{"id":"2507.01378","title":"RALLY: Role-Adaptive LLM-Driven Yoked Navigation for Agentic UAV Swarms","created":"2025-07-02","cited_by_count":7,"area":"agents"},{"id":"2607.13591","title":"Memory as a Controlled Process: Learned Adaptive Memory Management for LLM Agents","created":"2026-07-15","cited_by_count":7,"area":"agents"},{"id":"2412.16325","title":"Towards Safe and Honest AI Agents with Neural Self-Other Overlap","created":"2024-12-20","cited_by_count":6,"area":"agents"},{"id":"2504.12961","title":"QLLM: Do We Really Need a Mixing Network for Credit Assignment in Multi-Agent Reinforcement Learning?","created":"2025-04-17","cited_by_count":6,"area":"agents"},{"id":"2506.06366","title":"AI Agent Behavioral Science","created":"2025-06-04","cited_by_count":6,"area":"agents"},{"id":"2509.14680","title":"LEED: A Highly Efficient and Scalable LLM-Empowered Expert Demonstrations Framework for Multi-Agent Reinforcement Learning","created":"2025-09-18","cited_by_count":6,"area":"agents"},{"id":"2503.03505","title":"Parallelized Planning-Acting for Efficient LLM-based Multi-Agent Systems in Minecraft","created":"2025-03-05","cited_by_count":5,"area":"agents"},{"id":"2512.09629","title":"End-to-end PDDL Planning with Hardcoded and Dynamic Agents","created":"2025-12-10","cited_by_count":5,"area":"agents"},{"id":"2605.02801","title":"Reinforcement Learning for LLM-based Multi-Agent Systems through Orchestration Traces","created":"2026-05-04","cited_by_count":5,"area":"agents"},{"id":"2310.04579","title":"Self-Confirming Transformer for Belief-Conditioned Adaptation in Offline Multi-Agent Reinforcement Learning","created":"2023-10-06","cited_by_count":4,"area":"agents"},{"id":"2405.19328","title":"Normative Modules: A Generative Agent Architecture for Learning Norms that Supports Multi-Agent Cooperation","created":"2024-05-29","cited_by_count":4,"area":"agents"},{"id":"2506.24019","title":"Ella: Embodied Social Agents with Lifelong Memory","created":"2025-06-30","cited_by_count":4,"area":"agents"},{"id":"2604.00722","title":"LangMARL: Natural Language Multi-Agent Reinforcement Learning","created":"2026-04-01","cited_by_count":4,"area":"agents"},{"id":"2310.16730","title":"MultiPrompter: Cooperative Prompt Optimization with Multi-Agent Reinforcement Learning","created":"2023-10-25","cited_by_count":3,"area":"agents"},{"id":"2405.16854","title":"Knowing What Not to Do: Leverage Language Model Insights for Action Space Pruning in Multi-agent Reinforcement Learning","created":"2024-05-27","cited_by_count":3,"area":"agents"},{"id":"2505.18595","title":"MisoDICE: Multi-Agent Imitation from Unlabeled Mixed-Quality Demonstrations","created":"2025-05-24","cited_by_count":3,"area":"agents"},{"id":"2506.04251","title":"Language-Driven Coordination and Learning in Multi-Agent Simulation Environments","created":"2025-06-01","cited_by_count":3,"area":"agents"},{"id":"2512.06196","title":"ARCANE: A Multi-Agent Framework for Interpretable and Configurable Alignment","created":"2025-12-05","cited_by_count":3,"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":"2602.06030","title":"PhysicsAgentABM: Physics-Guided Generative Agent-Based Modeling","created":"2026-02-05","cited_by_count":3,"area":"agents"},{"id":"2502.10148","title":"Closed-Loop Vision-Language Planning for Multi-Agent Coordination","created":"2025-02-14","cited_by_count":2,"area":"agents"},{"id":"2509.12927","title":"HLSMAC: A New StarCraft Multi-Agent Challenge for High-Level Strategic Decision-Making","created":"2025-09-16","cited_by_count":2,"area":"agents"},{"id":"2509.21828","title":"Preference-Guided Learning for Sparse-Reward Multi-Agent Reinforcement Learning","created":"2025-09-26","cited_by_count":2,"area":"agents"},{"id":"2602.13255","title":"DPBench: Structural Determinants of Multi-Agent LLM Coordination Under Simultaneous Resource Contention","created":"2026-02-02","cited_by_count":2,"area":"agents"},{"id":"2602.14471","title":"Socially-Weighted Alignment: A Game-Theoretic Framework for Multi-Agent LLM Systems","created":"2026-02-16","cited_by_count":2,"area":"agents"},{"id":"2602.21515","title":"Training Generalizable Collaborative Agents via Strategic Risk Aversion","created":"2026-02-25","cited_by_count":2,"area":"agents"},{"id":"2603.23406","title":"Beyond Preset Identities: How Agents Form Stances and Boundaries in Generative Societies","created":"2026-03-24","cited_by_count":2,"area":"agents"},{"id":"2604.02674","title":"Do Agent Societies Develop Intellectual Elites? The Hidden Power Laws of Collective Cognition in LLM Multi-Agent Systems","created":"2026-04-03","cited_by_count":2,"area":"agents"},{"id":"2605.18077","title":"LLM-Guided Communication for Cooperative Multi-Agent Reinforcement Learning","created":"2026-05-18","cited_by_count":2,"area":"agents"},{"id":"2606.09961","title":"3SPO: State-Score-Supervised Policy Optimization for LLM Agents","created":"2026-06-08","cited_by_count":2,"area":"agents"},{"id":"2510.00022","title":"Learning to Lead Themselves: Agentic AI in MAS using MARL","created":"2025-09-24","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":"2510.06151","title":"LLMs as Policy-Agnostic Teammates: A Case Study in Human Proxy Design for Heterogeneous Agent Teams","created":"2025-10-07","cited_by_count":1,"area":"agents"},{"id":"2511.19253","title":"MAESTRO: Multi-Agent Environment Shaping through Task and Reward Optimization","created":"2025-11-24","cited_by_count":1,"area":"agents"},{"id":"2604.22452","title":"Superminds Test: Actively Evaluating Collective Intelligence of Agent Society via Probing Agents","created":"2026-04-24","cited_by_count":1,"area":"agents"},{"id":"2605.12857","title":"ChipMATE: Multi-Agent Training via Reinforcement Learning for Enhanced RTL Generation","created":"2026-05-13","cited_by_count":1,"area":"agents"},{"id":"2605.15207","title":"TeamTR: Trust-Region Fine-Tuning for Multi-Agent LLM Coordination","created":"2026-05-01","cited_by_count":1,"area":"agents"},{"id":"2605.19140","title":"Learning to Hand Off: Provably Convergent Workflow Learning under Interface Constraints","created":"2026-05-18","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":"2606.04484","title":"AgentJet: A Distributed Swarm Training Framework for Agentic Reinforcement Learning","created":"2026-06-03","cited_by_count":1,"area":"agents"},{"id":"2608.10299","title":"Co-Evolution in Agentic Systems: Toward Self-Directed Evolution Beyond Human Design","created":"2026-08-10","cited_by_count":1,"area":"agents"},{"id":"2608.18092","title":"Position: Multi-Agent Systems Should Prioritize Concurrency Control","created":"2026-06-06","cited_by_count":1,"area":"agents"},{"id":"2505.18457","title":"EdgeAgentX: A Novel Framework for Agentic AI at the Edge in Military Communication Networks","created":"2025-05-24","cited_by_count":0,"area":"agents"},{"id":"2505.23803","title":"MultiPhishGuard: An Explainable and Adaptive Multi-Agent LLM System for Phishing Email Detection","created":"2025-05-26","cited_by_count":0,"area":"agents"},{"id":"2509.13368","title":"$Agent^2$: An Agent-Generates-Agent Framework for Reinforcement Learning Automation","created":"2025-09-16","cited_by_count":0,"area":"agents"},{"id":"2510.18476","title":"Probabilistic Modeling of Intentions in Socially Intelligent LLM Agents","created":"2025-10-21","cited_by_count":0,"area":"agents"},{"id":"2510.18515","title":"Socialized Learning and Emergent Behaviors in Multi-Agent Systems based on Multimodal Large Language Models","created":"2025-10-21","cited_by_count":0,"area":"agents"},{"id":"2510.24030","title":"Human Machine Social Hybrid Intelligence:A Collaborative Decision Making Framework for Large Model Agent Groups and Human Experts","created":"2025-10-28","cited_by_count":0,"area":"agents"},{"id":"2511.10687","title":"Who Gets the Reward & Who Gets the Blame? Evaluation-Aligned Training Signals for Multi-LLM Agents","created":"2025-11-11","cited_by_count":0,"area":"agents"},{"id":"2512.03285","title":"A Gossip-Enhanced Communication Substrate for Agentic AI: Toward Decentralized Coordination in Large-Scale Multi-Agent Systems","created":"2025-12-02","cited_by_count":0,"area":"agents"},{"id":"2512.21024","title":"Policy-Conditioned Policies for Multi-Agent Task Solving","created":"2025-12-24","cited_by_count":0,"area":"agents"},{"id":"2512.24609","title":"Reinforcement Learning-Augmented LLM Agents for Collaborative Decision Making and Performance Optimization","created":"2025-12-31","cited_by_count":0,"area":"agents"},{"id":"2601.21861","title":"Spatiotemporal Continual Federated Learning for Agentic Multi-UAV Edge Networks: Mitigating Catastrophic Forgetting","created":"2026-01-29","cited_by_count":0,"area":"agents"},{"id":"2603.00130","title":"Agentic Hives: Equilibrium, Indeterminacy, and Endogenous Cycles in Self-Organizing Multi-Agent Systems","created":"2026-02-23","cited_by_count":0,"area":"agents"},{"id":"2603.03768","title":"Cognition to Control - Multi-Agent Learning for Human-Humanoid Collaborative Transport","created":"2026-03-04","cited_by_count":0,"area":"agents"},{"id":"2603.12031","title":"Agentic-Kube: A Graph-Enhanced Multi-Agent Reinforcement Learning Framework for Multi-Objective Kubernetes Scheduling","created":"2026-03-12","cited_by_count":0,"area":"agents"},{"id":"2603.15418","title":"MA-VLCM: A Vision Language Critic Model for Value Estimation of Policies in Multi-Agent Team Settings","created":"2026-03-16","cited_by_count":0,"area":"agents"},{"id":"2604.17191","title":"Do LLM-derived graph priors improve multi-agent coordination?","created":"2026-04-19","cited_by_count":0,"area":"agents"},{"id":"2604.23557","title":"DLM: Unified Decision Language Models for Offline Multi-Agent Sequential Decision Making","created":"2026-04-26","cited_by_count":0,"area":"agents"},{"id":"2604.27358","title":"Safe Bilevel Delegation (SBD): A Formal Framework for Runtime Delegation Safety in Multi-Agent Systems","created":"2026-04-30","cited_by_count":0,"area":"agents"},{"id":"2605.07863","title":"ADKO: Agentic Decentralized Knowledge Optimization","created":"2026-05-08","cited_by_count":0,"area":"agents"},{"id":"2605.24490","title":"Market Regime Council for Dynamic Credit Assignment in Multi-Agent LLM Decision Systems","created":"2026-05-23","cited_by_count":0,"area":"agents"},{"id":"2606.20014","title":"Hierarchical Control in Multi-Agent Games: LLM-based Planning and RL Execution","created":"2026-06-18","cited_by_count":0,"area":"agents"},{"id":"2607.04470","title":"Regime-Conditional Stabilisation of LLM-Augmented Cooperative Multi-Agent Reinforcement Learning","created":"2026-07-05","cited_by_count":0,"area":"agents"},{"id":"2608.09485","title":"Capability Is Not Propensity: Measuring Pressure-Robust Cooperative Behavior in Civic LLM Agents","created":"2026-08-10","cited_by_count":0,"area":"agents"},{"id":"2608.11207","title":"Dynamic Governance of Multi-LLM Agent Systems for Collaborative Conversational Outcomes","created":"2026-04-25","cited_by_count":0,"area":"agents"},{"id":"2608.18110","title":"Emergence of Agentic AI: A Review on Evolution, Background, Working Principles, Applications, Adoption Factors, and Future Research Directions","created":"2026-06-20","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":"2609.08452","title":"SRPO: Setwise Relative Policy Optimization for Multi-Agent LLMs","created":"2026-09-08","cited_by_count":0,"area":"agents"},{"id":"2609.18520","title":"AeroWeaver: An Embodied-Agent Harness for Weaving Aerial Skills into Distributed, Adaptive Swarm Execution","created":"2026-09-16","cited_by_count":0,"area":"agents"}],"next_cursor":"100"}