HTN规划作为多服务器MCP工具编排的协调层
HTN Planning as a Coordination Layer for Multi-Server MCP Tool Orchestration
浏览论文内容
中文总结 AI 辅助
提出一种基于HTN规划的协调架构,为多服务器MCP工具编排生成可验证计划并由运行时中间件确定性执行,解决大语言模型编排的非确定性问题,已在五个领域及八个实时服务器上验证。
中文摘要 AI 辅助
模型上下文协议(MCP)通过设计将服务器隔离:只有主机可以编排跨服务器的工作流。当主机是大语言模型时,所产生的编排是非确定性的、不可复现的,并且每次工具调用都需要一次推理往返。我们提出了一种协调架构,其中层次任务网络(HTN)规划器生成一次可验证的跨服务器计划,运行时中间件在多个MCP服务器上确定性地执行该计划,通过在执行时替换的模板机制(\verb|${context.X}|)绑定跨操作的数据依赖。该架构镜像了MCP的隔离约束:每个复合任务分解为服务器本地的原始操作,跨服务器的数据流在执行时通过JSON路径输出提取器绑定。我们在五个HTN领域上实例化了该架构,涵盖实验室机器人、生物信息学和多尺度建模,并展示了从基于浏览器的计划控制器到八个实时第三方MCP服务器查询真实生物数据库的端到端执行。
英文摘要
The Model Context Protocol (MCP) isolates servers by design: only the host can orchestrate cross-server workflows. When the host is a large language model, the resulting orchestrations are non-deterministic, non-reproducible, and pay one inference round-trip per tool call. We present a coordination architecture in which a Hierarchical Task Network (HTN) planner generates a verifiable cross-server plan once, and a runtime middleware executes it deterministically across multiple MCP servers, binding cross-action data dependencies via a template mechanism (\verb|${context.X}|) substituted at execution time. The architecture mirrors MCP's isolation constraint: each compound task decomposes into server-local primitive actions, and inter-server data flow is bound at execution time via JSON-path output extractors. We instantiate the architecture on five HTN domains spanning laboratory robotics, bioinformatics and multiscale modelling, and demonstrate end-to-end execution from a browser-based plan controller against eight live third-party MCP servers querying real biological databases.
发表机构
- RIKEN(理化学研究所)
- Cosmic AI(宇宙人工智能公司)
机构由 AI 辅助整理,请以论文原文为准。