SACHI: Structured Agent Coordination via Holistic Information Integration in Multi-Agent Reinforcement Learning

• URL: http://arxiv.org/abs/2605.08391v1
• Date: Fri, 08 May 2026 19:00:34 GMT
• Title: SACHI: Structured Agent Coordination via Holistic Information Integration in Multi-Agent Reinforcement Learning
• Abstract summary: Multi-agent reinforcement learning agents that act on partial local observations face a fundamental information bottleneck.<n>We propose textitstructured agent coordination via holistic information integration, or SACHI, in which graph transformer convolutions over an inter-agent coordination graph enrich each agent's representation with content-dependent signals from teammates prior to action selection.<n>SACHI consistently matches or outperforms the best baseline on every task, and rigorous aggregate statistical analyses, including normalized metrics with bootstrap confidence intervals, Friedman ranking, and performance profiling, confirm that this advantage is statistically significant, robust across environments, and not attributable to increased model capacity
• Score: 7.702487800530373
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Cooperative multi-agent reinforcement learning agents that act on partial local observations face a fundamental information bottleneck: the knowledge needed to select jointly optimal actions is scattered across the team, yet each agent must commit to a decision without access to its teammates' observations, intentions, or chosen actions. Existing methods either ignore this bottleneck, compress it into a scalar mixing signal, or route around it with learned communication channels. Framing action coordination as a problem of structured information integration among agents, we propose \textit{structured agent coordination via holistic information integration}, or SACHI, in which graph transformer convolutions over an inter-agent coordination graph enrich each agent's representation with receiver-sensitive, content-dependent signals from teammates prior to action selection. We evaluate SACHI across five cooperative tasks spanning spatial, communicative, and adversarial coordination challenges against twelve baselines. SACHI consistently matches or outperforms the best baseline on every task, and rigorous aggregate statistical analyses, including normalized metrics with bootstrap confidence intervals, Friedman ranking, and performance profiling, confirm that this advantage is statistically significant, robust across environments, and not attributable to increased model capacity. Parameter-matched ablations further trace the source of the gains to a single architectural property: the degree of content-dependence in the message-passing operator.

Related papers

• Improving the Efficiency of Language Agent Teams with Adaptive Task Graphs [52.26652574704317]
  Large language models (LLMs) are increasingly deployed in teams, yet existing coordination approaches often occupy two extremes.<n>We introduce Language Agent Teams for Task Evolution (LATTE), a framework for coordinating LLM teams inspired by distributed systems.
  arXiv  Detail & Related papers  (2026-05-07T14:19:17Z)
• SynAgent: Generalizable Cooperative Humanoid Manipulation via Solo-to-Cooperative Agent Synergy [59.86199649493784]
  Controllable cooperative humanoid manipulation is a fundamental yet challenging problem for embodied intelligence.<n>We present SynAgent, a framework that enables scalable and physically plausible cooperative manipulation.<n>In experiments, SynAgent significantly outperforms existing baselines in both cooperative imitation and trajectory-conditioned control.
  arXiv  Detail & Related papers  (2026-04-20T17:46:20Z)
• Self-Configurable Mesh-Networks for Scalable Distributed Submodular Bandit Optimization [6.522338519818377]
  We study how to scale distributed bandit submodular coordination under realistic communication constraints in bandwidth, data rate, and connectivity.<n>Our approach enables near-optimal action coordination by optimizing the agents' communication neighborhoods over time.<n>It is observed to converge faster, outperform benchmarks for bandit submodular coordination, and can even outperform benchmarks that are privileged with a priori knowledge of the environment.
  arXiv  Detail & Related papers  (2026-02-22T22:36:37Z)
• Safe Heterogeneous Multi-Agent RL with Communication Regularization for Coordinated Target Acquisition [14.31446990918297]
  This paper introduces a decentralized multi-agent reinforcement learning framework.<n>It enables structurally heterogeneous teams of agents to jointly discover and acquire randomly located targets.
  arXiv  Detail & Related papers  (2026-01-13T08:30:43Z)
• Learning to Interact in World Latent for Team Coordination [53.51290193631586]
  This work presents a novel representation learning framework, interactive world latent (IWoL), to facilitate team coordination in multi-agent reinforcement learning (MARL)<n>Our key insight is to construct a learnable representation space that jointly captures inter-agent relations and task-specific world information by directly modeling communication protocols.<n>Our representation can be used not only as an implicit latent for each agent, but also as an explicit message for communication.
  arXiv  Detail & Related papers  (2025-09-29T22:13:39Z)
• FeaKM: Robust Collaborative Perception under Noisy Pose Conditions [1.9626657740463982]
  We introduce FeaKM, a novel method that employs Feature-level Keypoints Matching to correct pose discrepancies among collaborating agents.<n>Our experimental results demonstrate that FeaKM significantly outperforms existing methods on the DAIR-V2X dataset.
  arXiv  Detail & Related papers  (2025-02-16T06:03:33Z)
• Communication Learning in Multi-Agent Systems from Graph Modeling Perspective [62.13508281188895]
  We introduce a novel approach wherein we conceptualize the communication architecture among agents as a learnable graph. We introduce a temporal gating mechanism for each agent, enabling dynamic decisions on whether to receive shared information at a given time.
  arXiv  Detail & Related papers  (2024-11-01T05:56:51Z)
• Learning Multi-Agent Communication from Graph Modeling Perspective [62.13508281188895]
  We introduce a novel approach wherein we conceptualize the communication architecture among agents as a learnable graph. Our proposed approach, CommFormer, efficiently optimize the communication graph and concurrently refines architectural parameters through gradient descent in an end-to-end manner.
  arXiv  Detail & Related papers  (2024-05-14T12:40:25Z)
• Distributed Adaptive Learning Under Communication Constraints [54.22472738551687]
  This work examines adaptive distributed learning strategies designed to operate under communication constraints. We consider a network of agents that must solve an online optimization problem from continual observation of streaming data.
  arXiv  Detail & Related papers  (2021-12-03T19:23:48Z)
• Who2com: Collaborative Perception via Learnable Handshake Communication [34.29310680302486]
  We propose the problem of collaborative perception, where robots can combine their local observations with those of neighboring agents in a learnable way to improve accuracy on a perception task. Inspired by networking communication protocols, we propose a multi-stage handshake communication mechanism where the neural network can learn to compress relevant information needed for each stage. We show that for the semantic segmentation task, our handshake communication method significantly improves accuracy by approximately 20% over decentralized baselines, and is comparable to centralized ones using a quarter of the bandwidth.
  arXiv  Detail & Related papers  (2020-03-21T04:16:22Z)

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.