{"ID":3052336,"CreatedAt":"2026-06-04T04:41:36.695875263Z","UpdatedAt":"2026-06-06T06:18:20.846448642Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.04494","arxiv_id":"2606.04494","title":"Beyond Prompt-Based Planning: MCP-Native Graph Planning-based Biomedical Agent System","abstract":"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.","short_abstract":"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 ecosystem...","url_abs":"https://arxiv.org/abs/2606.04494","url_pdf":"https://arxiv.org/pdf/2606.04494v1","authors":"[\"Zhangtianyi Chen\",\"Florensia Widjaja\",\"Wufei Dai\",\"Xiangjun Zhang\",\"Yuhao Shen\",\"Juexiao Zhou\"]","published":"2026-06-03T06:19:25Z","proceeding":"cs.AI","tasks":"[\"cs.AI\"]","methods":"[\"Generative Adversarial Network\"]","has_code":false}