用图结构统一生物工具接口，让智能体规划更准更快。
Beyond Prompt-Based Planning: MCP-Native Graph Planning-based Biomedical Agent System
- 将杂乱生物工具转为标准MCP服务，构建可检索的图谱。
- 任务规划仅需提取小规模子图，上下文压缩比达N/(h×m̄)。
- 适合需要高效执行复杂生物流程的研究者使用。
生物医学智能体有望自动化复杂生物学工作流，但现有系统面临两大瓶颈：生物信息工具接口和执行环境高度异构，且规划仍依赖扁平化提示检索工具描述。随着生物软件生态增长，工具覆盖与上下文大小耦合导致工具混淆、规划不稳定、执行低效。本文提出BioManus，一种基于图结构规划的MCP原生生物医学智能体。首先引入BioinfoMCP编译器，将异构生物信息软件转换为标准化MCP服务器，构建大规模可执行MCP生态；随后将该生态组织为包含工具、操作、数据类型和工作流阶段的类型化异构MCP图。推理时，BioManus检索紧凑的任务特定子图，合成操作级工作流骨架。此设计使规划复杂度与原始工具数量解耦，在高召回检索下实现上下文压缩比Θ(N / (h * m̄))，其中N为总工具数，h为工作流深度，m̄（远小于N）为每操作平均候选工具数。在BioAgentBench和LAB-Bench上的实验表明，BioManus在执行准确率、工作流有效性与上下文效率上均优于先进基线。本工作揭示范式转变：可扩展的生物医学推理需依赖结构化可执行能力图，而非不断扩大的提示级工具检索。
原文摘要 · Abstract (English)
Biomedical agents promise to automate complex biological workflows, yet current systems face two fundamental bottlenecks: bioinformatics tools are highly heterogeneous in interfaces and execution environments, while agent planning still relies on flat prompt-retrieved tool descriptions. As biomedical software ecosystems grow, this coupling between tool coverage and context size leads to tool confusion, unstable planning, and inefficient execution. We introduce BioManus, an MCP-native biomedical agent built on graph-scaffolded planning over structured biological capabilities. BioManus first introduces the BioinfoMCP Compiler, which converts heterogeneous bioinformatics software into standardized MCP servers, yielding a large executable MCP ecosystem. It then organizes this ecosystem as a typed heterogeneous MCP graph over tools, operations, datatypes, and workflow stages. At inference time, BioManus retrieves compact task-specific subgraphs, synthesizes operation-level workflow scaffolds. This design decouples planning complexity from raw tool inventory size, achieving a context compression ratio of Theta(N / (h * m_bar)) under high-recall retrieval, where N is the total tool count, h is the workflow horizon, and m_bar (much smaller than N) is the average number of candidate tools per operation. Experiments on BioAgentBench and LAB-Bench show that BioManus improves execution accuracy, workflow validity, and context efficiency over advanced biomedical agent baselines. This work suggests a paradigm shift: scalable biomedical reasoning requires structured executable capability graphs rather than increasingly larger prompt-level tool retrieval.
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。