{"total":13,"rows":[{"id":"2503.08683","title":"CoLMDriver: LLM-based Negotiation Benefits Cooperative Autonomous Driving","created":"2025-03-11","cited_by_count":13,"area":null},{"id":"2502.04028","title":"Deep Meta Coordination Graphs for Multi-agent Reinforcement Learning","created":"2025-02-06","cited_by_count":6,"area":null},{"id":"2507.01059","title":"Automated Vehicles Should be Connected with Natural Language","created":"2025-06-29","cited_by_count":5,"area":null},{"id":"2602.15776","title":"GlobeDiff: State Diffusion Process for Partial Observability in Multi-Agent Systems","created":"2026-02-17","cited_by_count":3,"area":null},{"id":"2509.06053","title":"PolicyEvolve: Evolving Programmatic Policies by LLMs for multi-player games via Population-Based Training","created":"2025-09-07","cited_by_count":1,"area":null},{"id":"2511.02762","title":"From Solo to Symphony: Orchestrating Multi-Agent Collaboration with Single-Agent Demos","created":"2025-11-04","cited_by_count":1,"area":null},{"id":"2511.09792","title":"Beyond Monotonicity: Revisiting Factorization Principles in Multi-Agent Q-Learning","created":"2025-11-12","cited_by_count":1,"area":null},{"id":"2503.11452","title":"Deep Learning Agents Trained For Avoidance Behave Like Hawks And Doves","created":"2025-03-14","cited_by_count":0,"area":null},{"id":"2505.12811","title":"Dynamic Sight Range Selection in Multi-Agent Reinforcement Learning","created":"2025-05-19","cited_by_count":0,"area":null},{"id":"2602.19223","title":"Characterizing MARL for Energy Control: A Multi-KPI Benchmark on the CityLearn Environment","created":"2026-02-22","cited_by_count":0,"area":null},{"id":"2602.22786","title":"QSIM: Mitigating Overestimation in Multi-Agent Reinforcement Learning via Action Similarity Weighted Q-Learning","created":"2026-02-26","cited_by_count":0,"area":null},{"id":"2606.24010","title":"Safe and Generalizable Hierarchical Multi-Agent RL via Constraint Manifold Control","created":"2026-06-22","cited_by_count":0,"area":null},{"id":"2606.30072","title":"ACPO: Agent-Chained Policy Optimization for Multi-Agent Reinforcement Learning","created":"2026-06-29","cited_by_count":0,"area":null}],"next_cursor":null}