mlsanityData to 14 Oct 2026

Multi-Agent Coordination via Multi-Level Communication

arXiv 2209.12713 ↗First posted 26 Sep 2022cs.MA cs.LGcited by 14

Not on the map. Why?

Abstract (arXiv)

The partial observability and stochasticity in multi-agent settings can be mitigated by accessing more information about others via communication. However, the coordination problem still exists since agents cannot communicate actual actions with each other at the same time due to the circular dependencies. In this paper, we propose a novel multi-level communication scheme, Sequential Communication (SeqComm). SeqComm treats agents asynchronously (the upper-level agents make decisions before the lower-level ones) and has two communication phases. In the negotiation phase, agents determine the priority of decision-making by communicating hidden states of observations and comparing the value of intention, obtained by modeling the environment dynamics. In the launching phase, the upper-level agents take the lead in making decisions and then communicate their actions with the lower-level agents. Theoretically, we prove the policies learned by SeqComm are guaranteed to improve monotonically and converge. Empirically, we show that SeqComm outperforms existing methods in various cooperative multi-agent tasks.

Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). Builds on 20 of its 43 references that are in the map. First posted on arXiv 26 Sep 2022.

Builds on

20 of 43 references.

References · 20

  1. 2015Trust Region Policy Optimizationcited by 2,580
  2. 2017Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environmentscited by 1,558
  3. 2019When to Trust Your Model: Model-Based Policy Optimizationcited by 773
  4. 2019The StarCraft Multi-Agent Challengecited by 597
  5. 2018Machine Theory of Mindcited by 226
  6. 2018TarMAC: Targeted Multi-Agent Communicationcited by 208
  7. 2018Learning Attentional Communication for Multi-Agent Cooperationcited by 175
  8. 2018Graph Convolutional Reinforcement Learningcited by 152
  9. 2019Deep Coordination Graphscited by 98
  10. 2019Learning to Schedule Communication in Multi-agent Reinforcement Learningcited by 93
  11. 2019Learning Nearly Decomposable Value Functions Via Communication Minimizationcited by 86
  12. 2018Searching with Consistent Prioritization for Multi-Agent Path Findingcited by 81
8 more
  1. 2019Probabilistic Recursive Reasoning for Multi-Agent Reinforcement Learningcited by 68
  2. 2018Modeling Others using Oneself in Multi-Agent Reinforcement Learningcited by 66
  3. 2020Learning Individually Inferred Communication for Multi-Agent Cooperationcited by 55
  4. 2019Efficient Communication in Multi-Agent Reinforcement Learning via Variance Based Controlcited by 46
  5. 2019Bi-level Actor-Critic for Multi-agent Coordinationcited by 39
  6. 2021Context-Aware Sparse Deep Coordination Graphscited by 28
  7. 2018Multiagent Soft Q-Learningcited by 26
  8. 2022Iterated Reasoning with Mutual Information in Cooperative and Byzantine Decentralized Teamingcited by 14

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 4; 2026: 9.

14 papers.

Sort:

By area:

  1. 2025Heterogeneous Swarms: Jointly Optimizing Model Roles and Weights for Multi-LLM Systemscited by 23
  2. 2024Offline Multi-Agent Reinforcement Learning via In-Sample Sequential Policy Optimizationcited by 15
  3. 2025Bandwidth-constrained Variational Message Encoding for Cooperative Multi-agent Reinforcement Learningcited by 3
  4. 2025Orchestrator: Active Inference for Multi-Agent Systems in Long-Horizon Taskscited by 2
  5. 2026How Task Structure Limits Multi-Agent Success: An Information-Theoretic Analysiscited by 1
  6. 2026HiComm: Hierarchical Communication for Multi-agent Reinforcement Learningcited by 1
  7. 2025From Capabilities to Performance: Evaluating Key Functional Properties of LLM Architectures in Penetration Testingcited by 0
  8. 2026Interference-Aware K-Step Reachable Communication in Multi-Agent Reinforcement Learningcited by 0
  9. 2026Communication Gain and Delay Cost Under Cross-Timestep Delays in Cooperative Multi-Agent Reinforcement Learningcited by 0
  10. 2026Breakthrough the Suboptimal Stable Point in Value-Factorization-Based Multi-Agent Reinforcement Learningcited by 0
  11. 2026Multi-Agent Decision-Focused Learning via Value-Aware Sequential Communicationcited by 0
  12. 2026Building Persona-Based Agents On Demand: Tailoring Multi-Agent Workflows to User Needscited by 0
2 more
  1. 2026When Does Hierarchy Help? Benchmarking Agent Coordination in Event-Driven Industrial Schedulingcited by 0
  2. 2026Communication-Efficient Digital-Twin Coordination for Heterogeneous LLM Embodied Agents over Computing Power Networkscited by 0