# Beyond Prompt-Based Planning: MCP-Native Graph Planning-based Biomedical Agent System

arXiv: https://arxiv.org/abs/2606.04494 · HTML: https://mlsanity.com/paper/2606.04494/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 166 references that are in the map.
- First posted on arXiv 3 Jun 2026.

## Builds on (most cited first, 17 of 17)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Gorilla: Large Language Model Connected with Massive APIs](https://mlsanity.com/paper/2305.15334/) (2023)
- [DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence](https://mlsanity.com/paper/2606.19348/) (2026)
- [LAB-Bench: Measuring Capabilities of Language Models for Biology Research](https://mlsanity.com/paper/2407.10362/) (2024)
- [RestGPT: Connecting Large Language Models with Real-World RESTful APIs](https://mlsanity.com/paper/2306.06624/) (2023)
- [GeneGPT: Augmenting Large Language Models with Domain Tools for Improved Access to Biomedical Information](https://mlsanity.com/paper/2304.09667/) (2023)
- [Yara Parser: A Fast and Accurate Dependency Parser](https://mlsanity.com/paper/1503.06733/) (2015)
- [MCP-Bench: Benchmarking Tool-Using LLM Agents with Complex Real-World Tasks via MCP Servers](https://mlsanity.com/paper/2508.20453/) (2025)
- [CellAgent: An LLM-driven Multi-Agent Framework for Automated Single-cell Data Analysis](https://mlsanity.com/paper/2407.09811/) (2024)
- [Prompt Sapper: A LLM-Empowered Production Tool for Building AI Chains](https://mlsanity.com/paper/2306.12028/) (2023)
- [BioAgent Bench: An AI Agent Evaluation Suite for Bioinformatics](https://mlsanity.com/paper/2601.21800/) (2026)
- [GeneAgent: Self-verification Language Agent for Gene Set Knowledge Discovery using Domain Databases](https://mlsanity.com/paper/2405.16205/) (2024)
- [ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox](https://mlsanity.com/paper/2605.10787/) (2026)
- [Biomedical systems biology workflow orchestration and execution with PoSyMed](https://mlsanity.com/paper/2604.20906/) (2026)

## Abstract (arXiv)

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.