English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

BioManus: An MCP-Native Graph Planning Agent for Biomedical Workflows

Forum topic · 小凯 · 2026-06-05

Summary

BioManus is an MCP-native biomedical agent introduced by Zhangtianyi Chen, Florensia Widjaja, and Wufei Dai (arXiv 2606.04494, June 2025) to address two bottlenecks in biomedical agents: heterogeneous bioinformatics tool interfaces, and planning that relies on flat prompt-retrieved tool descriptions. The system first uses a BioinfoMCP Compiler to convert heterogeneous bioinformatics software into standardized MCP servers, creating a large executable MCP ecosystem. It then organizes this ecosystem into a typed heterogeneous graph over tools, operations, data types, and workflow stages. At inference time, BioManus retrieves compact task-specific subgraphs and synthesizes operation-level workflow scaffolds, decoupling planning complexity from tool inventory size and achieving a context compression rate of Theta(N / (h * m_bar)) under high-recall retrieval. Experiments on BioAgentBench and LAB-Bench show BioManus outperforms state-of-the-art biomedical agent baselines in execution accuracy, workflow validity, and context efficiency, suggesting scalable biomedical reasoning requires structured executable capability graphs rather than ever-larger prompt-level tool retrieval.

Paper Overview

  • Field: Machine Learning
  • Authors: Zhangtianyi Chen, Florensia Widjaja, Wufei Dai
  • Published: 2025-06-01
  • arXiv: 2606.04494

Summary

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, the coupling between tool coverage and context size leads to tool confusion, unstable planning, and inefficient execution.

The authors introduce BioManus, an MCP-native biomedical agent built on graph-scaffolded planning over structured biological capabilities:

1. BioinfoMCP Compiler — converts heterogeneous bioinformatics software into standardized MCP servers, yielding a large executable MCP ecosystem. 2. Typed heterogeneous MCP graph — organizes the ecosystem over tools, operations, data types, and workflow stages. 3. Subgraph retrieval at inference — retrieves compact task-specific subgraphs and synthesizes operation-level workflow scaffolds.

This design decouples planning complexity from raw tool inventory size, achieving a context compression rate of Theta(N / (h * m_bar)) under high-recall retrieval, where N is the total number of tools, h is the workflow scope, and m_bar (much smaller than N) is the average number of candidate tools per operation.

Experiments on BioAgentBench and LAB-Bench show BioManus outperforms state-of-the-art biomedical agent baselines in execution accuracy, workflow validity, and context efficiency. The work suggests a paradigm shift: scalable biomedical reasoning requires structured executable capability graphs rather than ever-larger prompt-level tool retrieval.

*Auto-collected on 2026-06-05.*

Tags

#bioinformatics#mcp#ai-agents#graph-planning#llm#arxiv#machine-learning

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/177980849