HiComm: Hierarchical Communication for Multi-agent Reinforcement Learning

• URL: http://arxiv.org/abs/2606.29126v2
• Date: Wed, 01 Jul 2026 12:24:28 GMT
• Title: HiComm: Hierarchical Communication for Multi-agent Reinforcement Learning
• Abstract summary: We propose textscHiComm, a plug-in communication module that grounds messages in the sender's hierarchical observation.<n>textscHiComm is receiver-driven, and the hierarchy is resolved through a three-stage decoding process.<n>Experiments show that textscHiComm matches or outperforms representative learned communication baselines while reducing communication volume by up to $23times$ per receiver per episode.
• Score: 27.564924459355424
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Cooperative multi-agent reinforcement learning (MARL) often relies on communication to mitigate partial observability, yet most existing protocols treat messages as flat dense vectors detached from the structure of the observations they summarize. This design overlooks an important source of inductive bias in many cooperative environments, where observations naturally follow a hierarchy such as groups and entities. We propose \textsc{HiComm}, a plug-in communication module that grounds messages in the sender's hierarchical observation. \textsc{HiComm} is receiver-driven: the receiver issues a query, and the hierarchy is resolved through a three-stage decoding process that first selects a group, then a sender, and then an entity within that group, returning the corresponding feature slice as the message. This converts communication from unstructured vector transmission into structured information retrieval over the sender's observation hierarchy. We instantiate this mechanism with Straight-Through Gumbel-Softmax for differentiable discrete selection and a lightweight shared projection design that attaches to standard MARL pipelines. Experiments across cooperative MARL tasks with different observation structures and coordination demands show that \textsc{HiComm} matches or outperforms representative learned communication baselines while reducing communication volume by up to $23\times$ per receiver per episode.

Related papers

• Inference-Time Graph Engineering for Multi-Agent LLM Workflows [51.56038180639833]
  We introduce ReActNet, a training-free framework that compiles a query and a set of role-specialized agents into a sequence of directed communication graphs.<n>We show that ReActNet consistently improves over fixed-topology and learned-topology baselines while maintaining competitive inference cost.
  arXiv  Detail & Related papers  (2026-09-04T23:32:11Z)
• Beyond tokens: a unified framework for latent communication in LLM-based multi-agent systems [0.65268245109828]
  Multi-agent systems built on large language models (LLMs) have become a prevailing paradigm for tackling complex reasoning, planning, and tool-use tasks.<n>The dominant communication protocol in such systems is natural language: agents exchange messages token-by-token, verbalising their internal reasoning so that peers can read, verify, and respond.<n>A growing body of work therefore explores an alternative protocol -- latent communication, in which agents exchange continuous representations directly, bypassing the bottleneck of text generation.<n>This paper presents a unified framework for organising the rapidly expanding literature on latent communication.
  arXiv  Detail & Related papers  (2026-06-04T05:10:20Z)
• MOC: Multi-Order Communication in LLM-based Multi-Agent Systems [7.468643378553509]
  We propose the Multi-Order Communication scheme, which reconstructs the inter-agent communication to capture multi-hop dependencies and incorporates a structural message consolidation strategy to ensure efficiency.<n>Specifically, we formalize the communication mechanism to construct a structured multi-order evidence stream, and subsequently design a Semantic-Topological Merging algorithm to optimize semantic fidelity within token constraints.
  arXiv  Detail & Related papers  (2026-06-01T15:06:38Z)
• SOCO: Benchmarking Semantic Object Correspondence in Vision Foundation Models [63.28435103335999]
  We introduce SOCO, a new benchmark for Semantic Object Correspondence.<n>We show that vision foundation backbones encode strong semantic structure but transfer correspondences poorly across related categories.<n>We also show that LVLMs are stronger at text-prompted part localization than at visual-reference cross-image matching.
  arXiv  Detail & Related papers  (2026-05-29T17:58:48Z)
• GoAgent: Group-of-Agents Communication Topology Generation for LLM-based Multi-Agent Systems [55.12339141172908]
  GoAgent is a communication topology generation method that explicitly treats collaborative groups as the atomic units of MAS construction.<n>Experiments on six benchmarks demonstrate the state-of-the-art performance of GoAgent with 93.84% average accuracy while reducing token consumption by about 17%.
  arXiv  Detail & Related papers  (2026-03-20T06:21:32Z)
• SCoUT: Scalable Communication via Utility-Guided Temporal Grouping in Multi-Agent Reinforcement Learning [2.064923532131528]
  Communication can improve coordination in partially observed multi-agent reinforcement learning (MARL)<n>We introduce textbfSCoUT (textbfScalable textbfCommunication via textbfUtility-guided textbfTemporal grouping)<n>Agents are trained with a three-headed policy: environment action, send decision, and recipient selection.
  arXiv  Detail & Related papers  (2026-03-05T05:33:28Z)
• DyTopo: Dynamic Topology Routing for Multi-Agent Reasoning via Semantic Matching [15.07152520738373]
  We introduce DyTopo, a manager-guided multi-agent framework that reconstructs a sparse directed communication graph at each round.<n>Conditioned on the manager's round goal, each agent outputs lightweight natural-language query (need) and key (offer) descriptors.<n>DyTopo embeds these descriptors and performs semantic matching, routing private messages only along the induced edges.
  arXiv  Detail & Related papers  (2026-02-05T18:59:51Z)
• AnyMAC: Cascading Flexible Multi-Agent Collaboration via Next-Agent Prediction [77.62279834617475]
  We propose a new framework that rethinks multi-agent coordination through a sequential structure rather than a graph structure.<n>Our method focuses on two key directions: (1) Next-Agent Prediction, which selects the most suitable agent role at each step, and (2) Next-Context Selection, which enables each agent to selectively access relevant information from any previous step.
  arXiv  Detail & Related papers  (2025-06-21T18:34:43Z)
• RGMComm: Return Gap Minimization via Discrete Communications in Multi-Agent Reinforcement Learning [33.86277578441437]
  Communication is crucial for solving cooperative Multi-Agent Reinforcement Learning tasks in partially observable Markov Decision Processes. We propose the Return-Gap-Minimization Communication (RGMComm) algorithm, which is a surprisingly simple design of discrete message generation functions. Evaluations show that RGMComm significantly outperforms state-of-the-art multi-agent communication baselines.
  arXiv  Detail & Related papers  (2023-08-07T07:26:55Z)
• Semantic-Native Communication: A Simplicial Complex Perspective [50.099494681671224]
  We study semantic communication from a topological space perspective. A transmitter first maps its data into a $k$-order simplicial complex and then learns its high-order correlations. The receiver decodes the structure and infers the missing or distorted data.
  arXiv  Detail & Related papers  (2022-10-30T22:33:44Z)
• Learning Structured Communication for Multi-agent Reinforcement Learning [104.64584573546524]
  This work explores the large-scale multi-agent communication mechanism under a multi-agent reinforcement learning (MARL) setting. We propose a novel framework termed as Learning Structured Communication (LSC) by using a more flexible and efficient communication topology.
  arXiv  Detail & Related papers  (2020-02-11T07:19:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.