Learning to Communicate: Toward End-to-End Optimization of Multi-Agent Language Systems

• URL: http://arxiv.org/abs/2604.21794v1
• Date: Thu, 23 Apr 2026 15:53:25 GMT
• Title: Learning to Communicate: Toward End-to-End Optimization of Multi-Agent Language Systems
• Abstract summary: We propose DiffMAS, a training framework that treats latent communication as a learnable component of multi-agent systems.<n>Experiments show that DiffMAS consistently improves reasoning accuracy and decoding stability over single-agent inference, text-based multi-agent systems, and prior latent communication methods.
• Score: 30.327850022896286
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multi-agent systems built on large language models have shown strong performance on complex reasoning tasks, yet most work focuses on agent roles and orchestration while treating inter-agent communication as a fixed interface. Latent communication through internal representations such as key-value caches offers a promising alternative to text-based protocols, but existing approaches do not jointly optimize communication with multi-agent reasoning. Therefore we propose DiffMAS, a training framework that treats latent communication as a learnable component of multi-agent systems. DiffMAS performs parameter-efficient supervised training over multi-agent latent trajectories, enabling agents to jointly learn how information should be encoded and interpreted across interactions. Experiments on mathematical reasoning, scientific QA, code generation, and commonsense benchmarks show that DiffMAS consistently improves reasoning accuracy and decoding stability over single-agent inference, text-based multi-agent systems, and prior latent communication methods, achieving 26.7% on AIME24, 20.2% on GPQA-Diamond, and consistent gains across reasoning benchmarks.

Related papers

• 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)
• HyLaT: Efficient Multi-Agent Communication via Hybrid Latent-Text Protocol [54.411053382333996]
  HyLaT is a hybrid latent-text communication protocol that transmits elaborate cognitive signals through a latent channel for efficiency.<n>We introduce a two-stage training framework combining single-agent hybrid generation learning and multi-agent interactive co-training, enabling agents to generate and interpret hybrid messages.<n>Experiments demonstrate that HyLaT reduces communication overhead significantly while maintaining competitive task performance, with strong generalization and robustness across diverse settings.
  arXiv  Detail & Related papers  (2026-05-25T04:50:15Z)
• Learning to Communicate Locally for Large-Scale Multi-Agent Pathfinding [48.1609560841622]
  We present a learnable communication module tailored to enhance cooperation between agents via efficient feature sharing.<n>Our experiments show that the introduced method outperforms the existing learning-based MAPF solvers.
  arXiv  Detail & Related papers  (2026-05-08T12:05:08Z)
• Agent Q-Mix: Selecting the Right Action for LLM Multi-Agent Systems through Reinforcement Learning [68.85408801740228]
  We propose textbfAgent Q-Mix, a reinforcement learning framework that reformulates topology selection as a cooperative Multi-Agent Reinforcement Learning problem.<n>Our method learns decentralized communication decisions using Qmix value factorization, where each agent selects from a set of communication actions that jointly induce a round-wise communication graph.<n>Agent Q-Mix achieves the highest average accuracy compared to existing methods while demonstrating superior token efficiency and robustness against agent failure.
  arXiv  Detail & Related papers  (2026-04-01T00:38:24Z)
• MARTI-MARS$^2$: Scaling Multi-Agent Self-Search via Reinforcement Learning for Code Generation [64.2621682259008]
  Multi-Agent Reinforced Training and Inference Framework with Self-Search Scaling (MARTI-MARS2)<n>We propose a Multi-Agent Reinforced Training and Inference Framework with Self-Search Scaling (MARTI-MARS2) to integrate policy learning with multi-agent tree search.<n>We show that MARTI-MARS2 achieves 77.7%, outperforming strong baselines like GPT-5.1 on challenging code generation benchmarks.
  arXiv  Detail & Related papers  (2026-02-08T07:28:44Z)
• AgentRouter: A Knowledge-Graph-Guided LLM Router for Collaborative Multi-Agent Question Answering [51.07491603393163]
  tAgent is a framework that formulates multi-agent QA as a knowledge-graph-guided routing problem supervised by empirical performance signals.<n>By leveraging soft supervision and weighted aggregation of agent outputs, Agent learns principled collaboration schemes that capture the complementary strengths of diverse agents.
  arXiv  Detail & Related papers  (2025-10-06T23:20:49Z)
• MCP-Orchestrated Multi-Agent System for Automated Disinformation Detection [84.75972919995398]
  This paper presents a multi-agent system that uses relation extraction to detect disinformation in news articles.<n>The proposed Agentic AI system combines four agents: (i) a machine learning agent (logistic regression), (ii) a Wikipedia knowledge check agent, and (iv) a web-scraped data analyzer.<n>Results demonstrate that the multi-agent ensemble achieves 95.3% accuracy with an F1 score of 0.964, significantly outperforming individual agents and traditional approaches.
  arXiv  Detail & Related papers  (2025-08-13T19:14:48Z)
• Cued-Agent: A Collaborative Multi-Agent System for Automatic Cued Speech Recognition [17.451829471077858]
  Cued Speech (CS) is a visual communication system that combines lip-reading with hand coding to facilitate communication for individuals with hearing impairments.<n> Automatic CS Recognition (ACSR) aims to convert CS hand gestures and lip movements into text via AI-driven methods.<n>We propose the first collaborative multi-agent system for ACSR, named Cued-Agent.
  arXiv  Detail & Related papers  (2025-08-01T07:40:39Z)
• AgentMaster: A Multi-Agent Conversational Framework Using A2A and MCP Protocols for Multimodal Information Retrieval and Analysis [0.0]
  We present a pilot study of AgentMaster, a novel modular multi-protocol MAS framework with self-implemented A2A and MCP.<n>The system supports natural language interaction without prior technical expertise and responds to multimodal queries for tasks including information retrieval, question answering, and image analysis.<n>Overall, our proposed framework contributes to the potential capabilities of domain-specific, cooperative, and scalable conversational AI powered by MAS.
  arXiv  Detail & Related papers  (2025-07-08T03:34:26Z)
• 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)
• Research on Multi-Agent Communication and Collaborative Decision-Making Based on Deep Reinforcement Learning [0.0]
  This thesis studies the cooperative decision-making of multi-agent based on the Multi-Agent Proximal Policy Optimization algorithm. Different agents can alleviate the non-stationarity caused by local observations through information exchange between agents. The experimental results show that the improvement has achieved certain effects, which can better alleviate the non-stationarity of the multi-agent environment.
  arXiv  Detail & Related papers  (2023-05-23T14:20:14Z)

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.