为智能实验机器人与仪器间通信设计统一协议，解决自主科研系统集成难题。
LAP: An Agent-to-Instrument Protocol for Autonomous Science
- 提出LAP协议，实现智能体与物理仪器间的标准化通信。
- 支持仪器独占锁定、安全确认令牌和带不确定性的物理类型测量结果。
- 适用于自动化实验室、智能科研代理系统开发者与设备厂商。
自主科学正从示范走向基础设施建设。大语言模型代理可规划实验，自驾车实验室执行任务。然而，每个系统都需重新构建智能体与物理仪器之间的连接，受限于碎片化的供应商SDK和为确定性软件客户端设计的标准，难以适配具有概率性、目标导向的智能体。现有互操作协议（如Anthropic的MCP规范代理-工具接口，Google的A2A规范代理-代理接口）仅覆盖了智能体生态的两个边界，未涵盖智能体-仪器接口——该接口涉及状态化操作、安全关键任务、专属控制、物理实体及带有单位、校准和不确定性的真实测量。本文提出实验室智能体协议（LAP），填补此空白。LAP沿用A2A的对等、发现优先、任务生命周期结构，新增四个物理世界原语：(i) InstrumentCard，即带签名的能力与物理限制描述；(ii) 一级资源预留，实现仪器与样品的独占锁定；(iii) 安全围栏握手机制，通过加密绑定特定任务与参数的操作员确认令牌，管控危险或不可逆操作；(iv) MeasurementResult模式，确保每项结果具备物理类型（QUDT/UCUM）、校准锚定、不确定性承载，并可复现。文中定义角色、六层架构、JSON-RPC方法集、任务与安全状态机、错误模型及跨实验室联邦机制，并完整演示端到端闭环自主科研流程。LAP与A2A/MCP生态系统兼容，封装而非替代现有设备标准（如SiLA 2、OPC-UA）。
原文摘要 · Abstract (English)
Autonomous science is moving from demonstration to infrastructure. Large language model agents now plan experiments, and self-driving laboratories execute them. Yet every such system rebuilds the link between the reasoning agent and the physical instrument from scratch, against fragmented vendor SDKs and standards built for deterministic software clients rather than probabilistic, goal-directed agents. Recent agent-interoperability protocols clarify two of the three edges of an agentic ecosystem (Anthropic's Model Context Protocol (MCP) standardizes the agent-to-tool edge, and Google's Agent2Agent (A2A) the agent-to-agent edge), but neither models the agent-to-instrument edge, where operations are stateful, safety-critical, exclusively owned, physically embodied, and produce measurements with units, calibration, and uncertainty. We present the Lab Agent Protocol (LAP), a protocol design that fills this gap. LAP retains A2A's peer-to-peer, discovery-first, task-lifecycle structure and adds four physical-world primitives: (i) the InstrumentCard, a signed capability and physical-limit description; (ii) first-class reservation for exclusive instrument and sample locking; (iii) a safety-fence handshake with operator-confirmation tokens cryptographically bound to a specific task and its parameters, gating hazardous and irreversible operations; and (iv) a MeasurementResult schema that makes every result physically typed (QUDT/UCUM), calibration-anchored, uncertainty-bearing, and reproducible by construction. We specify roles, a six-layer architecture, the JSON-RPC method set, the task and safety state machines, the error model, and cross-laboratory federation, and walk a closed-loop autonomous campaign through the protocol end-to-end. LAP is transport-compatible with the A2A/MCP ecosystem and encapsulates rather than replaces existing device standards such as SiLA 2 and OPC-UA.
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。