用结构化信息通信，让多智能体系统更省 token 还更高效
What Should Agents Say? Action-state Communication for Efficient Multi-Agent Systems
- 将智能体间对话转为紧凑的动作状态记录，减少冗余语言
- 在不同系统结构中均实现性能不降、token 消耗显著降低
- 适合追求推理效率的生产级多智能体应用
基于大语言模型的多智能体系统通常依赖角色分工、流水线和轮次调度，但智能体间传递的内容常为自由形式的自然语言，导致令牌消耗激增，占用共享上下文窗口，影响系统性能与推理成本。我们分析了两种系统拓扑下的五种常见通信策略，发现无固定最优方案；有效通信始终保留下游智能体所需的动作中心信息。为此提出 PACT（协议化动作-状态通信与传输），将智能体间通信视为公共状态更新问题，将原始输出投影为紧凑的动作-状态记录再存入共享历史。在多种系统拓扑中，PACT 均显著改善性能-成本权衡，在保持或提升任务表现的同时大幅减少令牌使用。实际应用中，该方法使 OpenHands 的解决率在 -10% 令牌/解决情况下提升，对 SWE-agent 实现解决率不变但输入令牌减半。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。