{"total":24,"rows":[{"id":"2412.17767","title":"ResearchTown: Simulator of Human Research Community","created":"2024-12-23","cited_by_count":37,"area":null},{"id":"2405.18890","title":"Locally Estimated Global Perturbations are Better than Local Perturbations for Federated Sharpness-aware Minimization","created":"2024-05-29","cited_by_count":28,"area":null},{"id":"2502.19717","title":"Exponential Topology-enabled Scalable Communication in Multi-agent Reinforcement Learning","created":"2025-02-27","cited_by_count":7,"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":"2503.23626","title":"A Constrained Multi-Agent Reinforcement Learning Approach to Autonomous Traffic Signal Control","created":"2025-03-30","cited_by_count":3,"area":null},{"id":"2510.03930","title":"LLM Chemistry Estimation for Multi-LLM Recommendation","created":"2025-10-04","cited_by_count":3,"area":null},{"id":"2512.03528","title":"Multi-Agent Reinforcement Learning with Communication-Constrained Priors","created":"2025-12-03","cited_by_count":3,"area":null},{"id":"2512.11179","title":"Bandwidth-constrained Variational Message Encoding for Cooperative Multi-agent Reinforcement Learning","created":"2025-12-11","cited_by_count":3,"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":"2602.17062","title":"Retaining Suboptimal Actions to Follow Shifting Optima in Multi-Agent Reinforcement Learning","created":"2026-02-19","cited_by_count":3,"area":null},{"id":"2507.23604","title":"Hierarchical Message-Passing Policies for Multi-Agent Reinforcement Learning","created":"2025-07-31","cited_by_count":2,"area":null},{"id":"2604.13472","title":"Bridging MARL to SARL: An Order-Independent Multi-Agent Transformer via Latent Consensus","created":"2026-04-15","cited_by_count":2,"area":null},{"id":"2601.08327","title":"Safe Heterogeneous Multi-Agent RL with Communication Regularization for Coordinated Target Acquisition","created":"2026-01-13","cited_by_count":1,"area":null},{"id":"2606.29126","title":"HiComm: Hierarchical Communication for Multi-agent Reinforcement Learning","created":"2026-06-28","cited_by_count":1,"area":null},{"id":"2411.00382","title":"Communication Learning in Multi-Agent Systems from Graph Modeling Perspective","created":"2024-11-01","cited_by_count":0,"area":null},{"id":"2508.13661","title":"Communication-Enhanced Tutoring for Efficient Decentralized Multi-Agent Reinforcement Learning","created":"2025-08-19","cited_by_count":0,"area":null},{"id":"2602.08584","title":"Conditional Sequence Modeling for Safe Reinforcement Learning","created":"2026-02-09","cited_by_count":0,"area":null},{"id":"2603.04833","title":"SCoUT: Scalable Communication via Utility-Guided Temporal Grouping in Multi-Agent Reinforcement Learning","created":"2026-03-05","cited_by_count":0,"area":null},{"id":"2603.15054","title":"Interference-Aware K-Step Reachable Communication in Multi-Agent Reinforcement Learning","created":"2026-03-16","cited_by_count":0,"area":null},{"id":"2603.20279","title":"Learning Communication Between Heterogeneous Agents in Multi-Agent Reinforcement Learning for Autonomous Cyber Defence","created":"2026-03-17","cited_by_count":0,"area":null},{"id":"2604.05297","title":"Breakthrough the Suboptimal Stable Point in Value-Factorization-Based Multi-Agent Reinforcement Learning","created":"2026-04-07","cited_by_count":0,"area":null},{"id":"2605.17393","title":"Heterogeneous Information-Bottleneck Coordination Graphs for Multi-Agent Reinforcement Learning","created":"2026-05-17","cited_by_count":0,"area":null},{"id":"2605.21085","title":"Decoupling Communication from Policy: Robust MARL under Bandwidth Constraints","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2610.10302","title":"Continual Graph Multi-Agent Reinforcement Learning","created":"2026-10-07","cited_by_count":0,"area":null}],"next_cursor":null}