用标准化协议让AI团队高效协作，提升复杂任务表现
Agent Context Protocols Enhance Collective Inference
- 设计通用通信协议，通过结构化消息与依赖图实现多智能体协同
- 在长程网络助手任务中达28.3%准确率，优于商用系统
- 模块化设计，便于快速构建高性能通用AI代理
AI智能体在编码、推理和多模态理解等复杂任务上日益成熟。但构建通用系统需从单个智能体转向集体推理——即具备任务专长的多智能体通过结构化沟通与协作互补。当前协调多依赖模糊的自然语言，限制复杂交互并阻碍与领域专用智能体的互操作。本文提出智能体上下文协议（ACPs）：一种与领域和智能体无关的结构化通信、协调与容错协议族。ACPs结合（i）持久执行蓝图——显式存储中间输出的依赖图——与（ii）标准化消息模式，实现鲁棒且容错的多智能体集体推理。基于ACPs的通用系统在AssistantBench长程网络协助任务中达到28.3%准确率，生成的技术报告在人类评估中表现最佳，超越商业AI系统。ACPs高度模块化可扩展，使从业者能快速构建顶级通用智能体。
原文摘要 · Abstract (English)
AI agents have become increasingly adept at complex tasks such as coding, reasoning, and multimodal understanding. However, building generalist systems requires moving beyond individual agents to collective inference -- a paradigm where multi-agent systems with diverse, task-specialized agents complement one another through structured communication and collaboration. Today, coordination is usually handled with imprecise, ad-hoc natural language, which limits complex interaction and hinders interoperability with domain-specific agents. We introduce Agent context protocols (ACPs): a domain- and agent-agnostic family of structured protocols for agent-agent communication, coordination, and error handling. ACPs combine (i) persistent execution blueprints -- explicit dependency graphs that store intermediate agent outputs -- with (ii) standardized message schemas, enabling robust and fault-tolerant multi-agent collective inference. ACP-powered generalist systems reach state-of-the-art performance: 28.3 % accuracy on AssistantBench for long-horizon web assistance and best-in-class multimodal technical reports, outperforming commercial AI systems in human evaluation. ACPs are highly modular and extensible, allowing practitioners to build top-tier generalist agents quickly.
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。