What Should Agents Say? Action-state Communication for Efficient Multi-Agent Systems

• URL: http://arxiv.org/abs/2606.05304v1
• Date: Wed, 03 Jun 2026 18:00:22 GMT
• Title: What Should Agents Say? Action-state Communication for Efficient Multi-Agent Systems
• Abstract summary: We analyze five common inter-agent communication strategies across two multi-agent systems.<n>We propose the PACT (Protocolized Action-state Communication and Transmission), which treats inter-agent communication as a public state-update problem.<n>We show that PACT consistently improves the performance-cost trade-off, achieving comparable or stronger task performance with substantially fewer tokens.
• Score: 27.11156309236441
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multi-agent systems (MAS) built on large language models are typically organized around roles, pipelines, and turn schedules, while the content that agents pass to one another is often left as unconstrained natural language. However, this free-form communication can rapidly inflate token usage, consume the shared context window, and ultimately affect both system performance and inference cost. We analyze five common inter-agent communication strategies across two MAS topologies, finding that no fixed strategy is universally optimal. Instead, effective inter-agent messages consistently preserve action-centered information needed by downstream agents. Building on this, we propose the PACT (Protocolized Action-state Communication and Transmission), which treats inter-agent communication as a public state-update problem and projects each raw agent output into a compact action-state record before it enters shared history. Across different MAS topologies, PACT consistently improves the performance-cost trade-off, achieving comparable or stronger task performance with substantially fewer tokens. The gains extend to production coding harnesses: PACT lifts OpenHands' resolve rate at -10% tokens-per-resolved, and is resolve-neutral on SWE-agent while halving input tokens. Our code is publicly available at https://github.com/iNLP-Lab/PACT.

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)
• Learning to Communicate: Toward End-to-End Optimization of Multi-Agent Language Systems [30.327850022896286]
  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.
  arXiv  Detail & Related papers  (2026-04-23T15:53:25Z)
• GenericAgent: A Token-Efficient Self-Evolving LLM Agent via Contextual Information Density Maximization (V1.0) [56.81743709880371]
  Long-horizon large language model (LLM) agents are fundamentally limited by context.<n>We argue that long-horizon performance is determined not by context length, but by how much decision-relevant information is maintained within a finite context budget.<n>We present GenericAgent (GA), a general-purpose, self-evolving LLM agent system built around a single principle: information density and context.
  arXiv  Detail & Related papers  (2026-04-18T17:59:15Z)
• 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)
• 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)
• InterAgent: Physics-based Multi-agent Command Execution via Diffusion on Interaction Graphs [72.5651722107621]
  InterAgent is an end-to-end framework for text-driven physics-based multi-agent humanoid control.<n>We introduce an autoregressive diffusion transformer equipped with multi-stream blocks, which decouples proprioception, exteroception, and action to cross-modal interference.<n>We also propose a novel interaction graph exteroception representation that explicitly captures fine-grained joint-to-joint spatial dependencies.
  arXiv  Detail & Related papers  (2025-12-08T10:46:01Z)
• Anemoi: A Semi-Centralized Multi-agent System Based on Agent-to-Agent Communication MCP server from Coral Protocol [0.7288110873705294]
  Anemoi is a semi-centralized MAS built on the Agent-to-Agent (A2A) communication MCP server from Coral Protocol.<n>Unlike traditional designs, Anemoi enables structured and direct inter-agent collaboration, allowing all agents to monitor progress, assess results, identify bottlenecks, and propose refinements in real time.
  arXiv  Detail & Related papers  (2025-08-23T15:45:10Z)
• Augmenting Multi-Agent Communication with State Delta Trajectory [44.68954502805962]
  We propose a new communication protocol that transfers both natural language tokens and token-wise state transition from one agent to another.<n>We find that the sequence of state changes in LLMs after generating each token can better reflect the information hidden behind the inference process.<n>The experimental results show that multi-agent systems with SDE achieve SOTA performance compared to other communication protocols.
  arXiv  Detail & Related papers  (2025-06-24T00:38:25Z)
• 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)
• Runaway is Ashamed, But Helpful: On the Early-Exit Behavior of Large Language Model-based Agents in Embodied Environments [54.67512489842682]
  Large language models (LLMs) have demonstrated strong planning and decision-making capabilities in complex embodied environments.<n>We take a first step toward exploring the early-exit behavior for LLM-based agents.
  arXiv  Detail & Related papers  (2025-05-23T08:23:36Z)
• DroidSpeak: KV Cache Sharing for Cross-LLM Communication and Multi-LLM Serving [14.700431530275132]
  We introduce DroidSpeak, the first distributed LLM inference system that enables KV cache reuse across distributed nodes.<n>We show that DroidSpeak achieves up to 4x throughput improvement and about 3.1x faster prefill (time to first token)<n>Experiments on diverse datasets and model pairs demonstrate that DroidSpeak achieves up to 4x throughput improvement and about 3.1x faster prefill.
  arXiv  Detail & Related papers  (2024-11-05T05:41:41Z)
• Context-aware Communication for Multi-agent Reinforcement Learning [6.109127175562235]
  We develop a context-aware communication scheme for multi-agent reinforcement learning (MARL) In the first stage, agents exchange coarse representations in a broadcast fashion, providing context for the second stage. Following this, agents utilize attention mechanisms in the second stage to selectively generate messages personalized for the receivers. To evaluate the effectiveness of CACOM, we integrate it with both actor-critic and value-based MARL algorithms.
  arXiv  Detail & Related papers  (2023-12-25T03:33:08Z)
• Learning Individually Inferred Communication for Multi-Agent Cooperation [37.56115000150748]
  We propose Individually Inferred Communication (I2C) to enable agents to learn a prior for agent-agent communication. The prior knowledge is learned via causal inference and realized by a feed-forward neural network. I2C can not only reduce communication overhead but also improve the performance in a variety of multi-agent cooperative scenarios.
  arXiv  Detail & Related papers  (2020-06-11T14:07:57Z)

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.