Interference-Aware K-Step Reachable Communication in Multi-Agent Reinforcement Learning

• URL: http://arxiv.org/abs/2603.15054v1
• Date: Mon, 16 Mar 2026 10:07:33 GMT
• Title: Interference-Aware K-Step Reachable Communication in Multi-Agent Reinforcement Learning
• Abstract summary: Interference-Aware K-Step Reachable Communication (IA-KRC) is a novel framework that enhances cooperation via two core components.<n>IA-KRC enables substantially more persistent and efficient cooperation despite environmental interference.
• Score: 10.669533781311033
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Effective communication is pivotal for addressing complex collaborative tasks in multi-agent reinforcement learning (MARL). Yet, limited communication bandwidth and dynamic, intricate environmental topologies present significant challenges in identifying high-value communication partners. Agents must consequently select collaborators under uncertainty, lacking a priori knowledge of which partners can deliver task-critical information. To this end, we propose Interference-Aware K-Step Reachable Communication (IA-KRC), a novel framework that enhances cooperation via two core components: (1) a K-Step reachability protocol that confines message passing to physically accessible neighbors, and (2) an interference-prediction module that optimizes partner choice by minimizing interference while maximizing utility. Compared to existing methods, IA-KRC enables substantially more persistent and efficient cooperation despite environmental interference. Comprehensive evaluations confirm that IA-KRC achieves superior performance compared to state-of-the-art baselines, while demonstrating enhanced robustness and scalability in complex topological and highly dynamic multi-agent scenarios.

Related papers

• Task-Oriented Sensing and Covert Transmissions for Collaborative Multi-AUV Systems [67.63956000297922]
  This paper proposes a Sensed Information Value Realization Multi-Agent Reinforcement Learning (SVR-MARL) framework to characterize the utility of information for cooperative tasks.<n>The potential of the proposed framework to improve collaborative task efficiency while reducing unnecessary communication and exposure risks is demonstrated.
  arXiv  Detail & Related papers  (2026-07-15T14:29:25Z)
• A Token/KV-Cache Communication Media Selection and Resource Allocation Strategy for Multi-Agent Collaboration [9.576234748631647]
  We propose a joint design that integrates communication-media selection with wireless resource allocation.<n>We show that neither token-based transmission nor key-value ( KV) cache-based transmission is uniformly optimal across operating regimes.<n> numerically results confirm that, by adaptively coordinating the interaction media and bandwidth allocation over heterogeneous links, the proposed scheme markedly reduced E2E latency.
  arXiv  Detail & Related papers  (2026-05-25T04:50:45Z)
• Scalable Multiagent Reinforcement Learning with Collective Influence Estimation [5.050035210247092]
  This paper proposes a multiagent learning framework augmented with a Collective Influence Estimation Network.<n>By explicitly modeling the collective influence of other agents on the task object, each agent can infer critical interaction information.<n> Experimental results show that the proposed method achieves stable and efficient coordination under communication-limited environments.
  arXiv  Detail & Related papers  (2026-01-13T04:24:11Z)
• Communication to Completion: Modeling Collaborative Workflows with Intelligent Multi-Agent Communication [17.432061814666774]
  Communication to Completion (C2C) is a scalable framework for task oriented communication.<n>C2C reduces the task completion time by about 40% with acceptable communication costs.
  arXiv  Detail & Related papers  (2025-10-22T19:48:17Z)
• 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)
• 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)
• Towards Robust Multi-UAV Collaboration: MARL with Noise-Resilient Communication and Attention Mechanisms [5.666897565015641]
  We propose a multi-agent reinforcement learning (MARL) framework for UAV path planning based on the Counterfactual Multi-Agent Policy Gradients (COMA) algorithm.<n>The framework incorporates attention mechanism-based UAV communication protocol and training-deployment system.<n>Experiments conducted on both synthetic and real-world datasets demonstrate that our method outperforms existing algorithms in terms of path planning efficiency and robustness.
  arXiv  Detail & Related papers  (2025-03-04T08:05:14Z)
• 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)
• REVECA: Adaptive Planning and Trajectory-based Validation in Cooperative Language Agents using Information Relevance and Relative Proximity [5.365719315040012]
  REVECA is a novel cognitive architecture powered by GPT-4o-mini.<n>It enables efficient memory management, optimal planning, and cost-effective prevention of false planning.
  arXiv  Detail & Related papers  (2024-05-27T01:47:14Z)
• AntEval: Evaluation of Social Interaction Competencies in LLM-Driven Agents [65.16893197330589]
  Large Language Models (LLMs) have demonstrated their ability to replicate human behaviors across a wide range of scenarios. However, their capability in handling complex, multi-character social interactions has yet to be fully explored. We introduce the Multi-Agent Interaction Evaluation Framework (AntEval), encompassing a novel interaction framework and evaluation methods.
  arXiv  Detail & Related papers  (2024-01-12T11:18:00Z)
• Depthwise Convolution for Multi-Agent Communication with Enhanced Mean-Field Approximation [9.854975702211165]
  We propose a new method based on local communication learning to tackle the multi-agent RL (MARL) challenge. First, we design a new communication protocol that exploits the ability of depthwise convolution to efficiently extract local relations. Second, we introduce the mean-field approximation into our method to reduce the scale of agent interactions.
  arXiv  Detail & Related papers  (2022-03-06T07:42:43Z)
• Cascaded Human-Object Interaction Recognition [175.60439054047043]
  We introduce a cascade architecture for a multi-stage, coarse-to-fine HOI understanding. At each stage, an instance localization network progressively refines HOI proposals and feeds them into an interaction recognition network. With our carefully-designed human-centric relation features, these two modules work collaboratively towards effective interaction understanding.
  arXiv  Detail & Related papers  (2020-03-09T17:05:04Z)

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.