{"total":71,"rows":[{"id":"2203.08975","title":"A Survey of Multi-Agent Deep Reinforcement Learning with Communication","created":"2022-03-16","cited_by_count":104,"area":null},{"id":"2107.06857","title":"Scalable Evaluation of Multi-Agent Reinforcement Learning with Melting Pot","created":"2021-07-14","cited_by_count":99,"area":null},{"id":"2106.15691","title":"Deep Multiagent Reinforcement Learning: Challenges and Directions","created":"2021-06-29","cited_by_count":42,"area":null},{"id":"2107.07630","title":"Evaluation of Human-AI Teams for Learned and Rule-Based Agents in Hanabi","created":"2021-07-15","cited_by_count":40,"area":null},{"id":"2110.15349","title":"Learning to Ground Multi-Agent Communication with Autoencoders","created":"2021-10-28","cited_by_count":37,"area":null},{"id":"2302.01605","title":"Learning Zero-Shot Cooperation with Humans, Assuming Humans Are Biased","created":"2023-02-03","cited_by_count":37,"area":null},{"id":"2312.10256","title":"Multi-agent Reinforcement Learning: A Comprehensive Survey","created":"2023-12-15","cited_by_count":33,"area":null},{"id":"2206.07505","title":"Revisiting Some Common Practices in Cooperative Multi-Agent Reinforcement Learning","created":"2022-06-15","cited_by_count":32,"area":null},{"id":"2106.02067","title":"Learning to Draw: Emergent Communication through Sketching","created":"2021-06-03","cited_by_count":23,"area":null},{"id":"2103.08067","title":"Quasi-Equivalence Discovery for Zero-Shot Emergent Communication","created":"2021-03-14","cited_by_count":19,"area":null},{"id":"2110.05769","title":"Interpretation of Emergent Communication in Heterogeneous Collaborative Embodied Agents","created":"2021-10-12","cited_by_count":19,"area":null},{"id":"2101.10276","title":"Emergent Communication under Competition","created":"2021-01-25","cited_by_count":18,"area":null},{"id":"2202.03634","title":"Multi-Agent Path Finding with Prioritized Communication Learning","created":"2022-02-08","cited_by_count":18,"area":null},{"id":"2407.03302","title":"A Review of the Applications of Deep Learning-Based Emergent Communication","created":"2024-07-03","cited_by_count":17,"area":"deeprl"},{"id":"2308.02541","title":"Towards More Human-like AI Communication: A Review of Emergent Communication Research","created":"2023-08-01","cited_by_count":13,"area":null},{"id":"2102.12550","title":"Learning Emergent Discrete Message Communication for Cooperative Reinforcement Learning","created":"2021-02-24","cited_by_count":11,"area":null},{"id":"2110.14241","title":"Dynamic population-based meta-learning for multi-agent communication with natural language","created":"2021-10-27","cited_by_count":10,"area":null},{"id":"2309.06021","title":"Emergent Communication in Multi-Agent Reinforcement Learning for Future Wireless Networks","created":"2023-09-12","cited_by_count":9,"area":null},{"id":"2310.02435","title":"Multi-Agent Reinforcement Learning Based on Representational Communication for Large-Scale Traffic Signal Control","created":"2023-10-03","cited_by_count":7,"area":null},{"id":"2604.07821","title":"More Capable, Less Cooperative? When LLMs Fail At Zero-Cost Collaboration","created":"2026-04-09","cited_by_count":7,"area":null},{"id":"2106.11156","title":"Multi-Agent Curricula and Emergent Implicit Signaling","created":"2021-06-21","cited_by_count":6,"area":null},{"id":"2204.05669","title":"An Analysis of Discretization Methods for Communication Learning with Multi-Agent Reinforcement Learning","created":"2022-04-12","cited_by_count":6,"area":null},{"id":"2305.05116","title":"Communication-Robust Multi-Agent Learning by Adaptable Auxiliary Multi-Agent Adversary Generation","created":"2023-05-09","cited_by_count":6,"area":null},{"id":"2101.10253","title":"The emergence of visual semantics through communication games","created":"2021-01-25","cited_by_count":5,"area":null},{"id":"2504.03353","title":"Decentralized Collective World Model for Emergent Communication and Coordination","created":"2025-04-04","cited_by_count":5,"area":"wm"},{"id":"2508.06659","title":"In-Context Reinforcement Learning via Communicative World Models","created":"2025-08-08","cited_by_count":5,"area":"wm"},{"id":"2607.26773","title":"Do Latent Channels Actually Communicate? A Causal Audit of Latent Multi-Agent LLM","created":"2026-07-29","cited_by_count":5,"area":"agents"},{"id":"2104.09557","title":"Learning to Communicate with Strangers via Channel Randomisation Methods","created":"2021-04-19","cited_by_count":4,"area":null},{"id":"2211.01480","title":"Over-communicate no more: Situated RL agents learn concise communication protocols","created":"2022-11-02","cited_by_count":4,"area":null},{"id":"2607.00233","title":"From Signals to Structure: How Memory Architecture Drives Language Emergence in LLM Agents","created":"2026-06-30","cited_by_count":4,"area":"agents"},{"id":"2102.02304","title":"Improved Cooperation by Exploiting a Common Signal","created":"2021-02-03","cited_by_count":3,"area":null},{"id":"2105.12804","title":"TexRel: a Green Family of Datasets for Emergent Communications on Relations","created":"2021-05-26","cited_by_count":3,"area":null},{"id":"2111.01785","title":"PatchGame: Learning to Signal Mid-level Patches in Referential Games","created":"2021-11-02","cited_by_count":3,"area":null},{"id":"2305.08481","title":"Task-Oriented Communication Design at Scale","created":"2023-05-15","cited_by_count":3,"area":null},{"id":"2310.15597","title":"Emergent Communication in Interactive Sketch Question Answering","created":"2023-10-24","cited_by_count":3,"area":null},{"id":"2401.15059","title":"Fully Independent Communication in Multi-Agent Reinforcement Learning","created":"2024-01-26","cited_by_count":3,"area":null},{"id":"2105.05069","title":"Zero-Shot Generalization using Intrinsically Motivated Compositional Emergent Protocols","created":"2021-05-11","cited_by_count":2,"area":null},{"id":"2305.02632","title":"A framework for the emergence and analysis of language in social learning agents","created":"2023-05-04","cited_by_count":2,"area":null},{"id":"2305.10920","title":"Emergent Communication with Attention","created":"2023-05-18","cited_by_count":2,"area":null},{"id":"2305.12235","title":"Joining the Conversation: Towards Language Acquisition for Ad Hoc Team Play","created":"2023-05-20","cited_by_count":2,"area":null},{"id":"2306.01920","title":"Context-Aware Bayesian Network Actor-Critic Methods for Cooperative Multi-Agent Reinforcement Learning","created":"2023-06-02","cited_by_count":2,"area":null},{"id":"2403.17497","title":"Sharing the Cost of Success: A Game for Evaluating and Learning Collaborative Multi-Agent Instruction Giving and Following Policies","created":"2024-03-26","cited_by_count":2,"area":null},{"id":"2411.10173","title":"Semantics and Spatiality of Emergent Communication","created":"2024-11-15","cited_by_count":2,"area":null},{"id":"2505.21985","title":"Reward-Independent Messaging for Decentralized Multi-Agent Reinforcement Learning","created":"2025-05-28","cited_by_count":2,"area":null},{"id":"2506.02739","title":"Why do AI agents communicate in human language?","created":"2025-06-03","cited_by_count":2,"area":"agents"},{"id":"2102.04775","title":"Structured Diversification Emergence via Reinforced Organization Control and Hierarchical Consensus Learning","created":"2021-02-09","cited_by_count":1,"area":null},{"id":"2103.02150","title":"Inference-Based Deterministic Messaging For Multi-Agent Communication","created":"2021-03-03","cited_by_count":1,"area":null},{"id":"2105.03943","title":"gComm: An environment for investigating generalization in Grounded Language Acquisition","created":"2021-05-09","cited_by_count":1,"area":null},{"id":"2306.11336","title":"Cooperative Multi-Agent Learning for Navigation via Structured State Abstraction","created":"2023-06-20","cited_by_count":1,"area":null},{"id":"2402.04824","title":"Learning Communication Policies for Different Follower Behaviors in a Collaborative Reference Game","created":"2024-02-07","cited_by_count":1,"area":null},{"id":"2402.16247","title":"Learning Translations: Emergent Communication Pretraining for Cooperative Language Acquisition","created":"2024-02-26","cited_by_count":1,"area":null},{"id":"2503.15516","title":"In Pursuit of Predictive Models of Human Preferences Toward AI Teammates","created":"2025-01-31","cited_by_count":1,"area":null},{"id":"2609.32701","title":"Despite Instructions: Frontier Agents Improvise Covert Channels at Test Time","created":"2026-09-26","cited_by_count":1,"area":"agents"},{"id":"2101.11739","title":"Compositionality Through Language Transmission, using Artificial Neural Networks","created":"2021-01-27","cited_by_count":0,"area":null},{"id":"2109.09390","title":"Socially Supervised Representation Learning: the Role of Subjectivity in Learning Efficient Representations","created":"2021-09-20","cited_by_count":0,"area":null},{"id":"2110.08203","title":"Shared Visual Representations of Drawing for Communication: How do different biases affect human interpretability and intent?","created":"2021-10-15","cited_by_count":0,"area":null},{"id":"2111.11129","title":"Multi-lingual agents through multi-headed neural networks","created":"2021-11-22","cited_by_count":0,"area":null},{"id":"2306.03830","title":"Inductive Bias for Emergent Communication in a Continuous Setting","created":"2023-06-06","cited_by_count":0,"area":null},{"id":"2308.04844","title":"Scalability of Message Encoding Techniques for Continuous Communication Learned with Multi-Agent Reinforcement Learning","created":"2023-08-09","cited_by_count":0,"area":null},{"id":"2308.04938","title":"An In-Depth Analysis of Discretization Methods for Communication Learning using Backpropagation with Multi-Agent Reinforcement Learning","created":"2023-08-09","cited_by_count":0,"area":null},{"id":"2401.15840","title":"Emergent Explainability: Adding a causal chain to neural network inference","created":"2024-01-29","cited_by_count":0,"area":null},{"id":"2602.17737","title":"NestRL: A Nested Training Regime for Mutual Adaptation in Human-AI Teaming","created":"2026-02-18","cited_by_count":0,"area":null},{"id":"2604.08728","title":"Wireless Communication Enhanced Value Decomposition for Multi-Agent Reinforcement Learning","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2609.28581","title":"Auditability Is Not One Property: Rule Overlap, Behavioural Agreement, and Composition in Reinforcement Learning","created":"2026-09-23","cited_by_count":0,"area":"deeprl"},{"id":"2609.34373","title":"Emergence, Not Bandwidth: Physical Coupling and the Limits of Learned Multi-Agent Communication","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.34444","title":"Social Circuits behind Multi-agent Echo Chambers","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2610.05041","title":"Communication Shapes Collective Inference in Self-Adapting LLM Societies: Evidence from Mafia","created":"2026-10-04","cited_by_count":0,"area":null},{"id":"2610.14449","title":"Jevolution: A Framework for Studying Communication and Collective Dynamics in AI Agents","created":"2026-10-10","cited_by_count":0,"area":null},{"id":"2610.15163","title":"Sanzaru: Benchmarking Protocol Formation under Epistemic & Communication Asymmetry","created":"2026-10-10","cited_by_count":0,"area":null},{"id":"2610.17409","title":"Position: Beyond Training Time, Test-Time Coordination is Essential for Cooperative MARL","created":"2026-10-12","cited_by_count":0,"area":null},{"id":"2610.18727","title":"On the Monitorability of Natural Language Autoencoders: Identification vs Discrimination","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}