AECP 协议让多智能体协作编程测试通过率提升 28.2%
AECP: Artifact-Exclusive Communication Protocol for Multi-Agent Code Generation
多智能体写代码总互相丢信息？这篇论文把协调交给框架来做，通过率提升 28.2%，还顺带堵住了恶意指令传播。
AECP（Artifact-Exclusive Communication Protocol）要求多个编码智能体只通过结构化工件通信，由执行框架在智能体访问相关代码时注入发现、检查实现是否违背接口约定。在 Doc2Repo、NL2Repo 和 CodeProjectEval 三个基准上，使用 Opus-4.8 和 DeepSeek-V4-Flash 等闭源与开源模型，相比自由文本消息协作，平均测试通过率提高 28.2%，平均耗时缩短 16.5%。该方式还阻断了恶意指令在智能体间的传播，触达率从 95% 降到 0%，被恶意执行率从 40% 降到 0%。
AECP: Artifact-Exclusive Communication Protocol for Multi-Agent Code Generation
As AI agents increasingly tackle complex repository-level coding tasks, distributing work across multiple agents is a natural way to scale beyond the capabilities of a single agent. To coordinate their interdependent work, these agents share findings and agree on interfaces between modules. However, exchanged information often serves only as context, leaving individual agents to interpret it and incorporate it into subsequent work. Consequently, shared findings may go unused and deviations from interface agreements may go undetected, undermining the reliability and efficiency of collaboration. This motivates moving part of the coordination responsibility from individual agents to the execution harness. To make shared information actionable during execution, we introduce the Artifact-Exclusive Communication Protocol (AECP). AECP requires agents to communicate exclusively through structured artifacts and specifies how the harness processes them. The harness supplies findings when agents access relevant code, screens implementations for mismatches with recorded interface commitments, and requires affected agents to revisit revised agreements. These coordination steps become part of harness execution rather than actions that agents must initiate from prior messages. Across Doc2Repo, NL2Repo, and CodeProjectEval, using closed- and open-source models including Opus-4.8 and DeepSeek-V4-Flash, AECP improves average test pass rate by 28.2% and reduces average wall time by 16.5% relative to an agent team using free-form inter-agent messages. Artifact-exclusive communication also blocks the relay of malicious instructions between agents, reducing how often they reach other agents from 95% to 0% and how often those agents act on them from 40% to 0%.
