# PACT：行动状态通信实现高效多智能体系统

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-06-03 08:00
- AIHOT 分数：46
- AIHOT 链接：https://aihot.virxact.com/items/cmq7f3aiy02jisl5w5alsqtrp
- 原文链接：https://arxiv.org/abs/2606.05304

## AI 摘要

多智能体系统（MAS）中自由自然语言通信会导致token浪费和上下文膨胀。分析五种通信策略后发现无固定策略最优，但有效消息总包含下游智能体所需的行动中心信息。为此提出PACT协议，将通信视为公共状态更新问题，把每个智能体原始输出压缩为紧凑的行动状态记录再写入共享历史。PACT在不同MAS拓扑中均能实现相当或更强任务性能，同时大幅减少token消耗：在OpenHands上以每个已解决问题token消耗减少10%的代价提升解决率，在SWE-agent上解决率不变但输入token减半。代码已公开。

## 正文

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.