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

• URL: http://arxiv.org/abs/2606.04494v1
• Date: Wed, 03 Jun 2026 06:19:25 GMT
• Title: Beyond Prompt-Based Planning: MCP-Native Graph Planning-based Biomedical Agent System
• Abstract summary: We introduce BioManus, an MCP-native biomedical agent built on graph-scaffolded planning over structured biological capabilities.<n>We show that BioManus improves execution accuracy, workflow validity, and context efficiency over advanced biomedical agent baselines.
• Score: 0.8857568447033265
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• 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.

Related papers

• Bioinfoysis Technical Report [22.71562563762352]
  We introduce textbfBioinfoysis, a multi-agent harness that represents each request as a persistent artifact-grounded analysis run.<n>A controlled runtime validates generated scripts, tables, and figures before they are used in downstream analysis or reporting.<n>Across four underlying language models, Bioinfoysis increases average accuracy from 27.81% to 64.13% on SeqQA2 and from 3.13% to 31.25% on DbQA2.
  arXiv  Detail & Related papers  (2026-09-03T13:59:00Z)
• AIMBio-Mat: An AI-Native FAIR Platform for Closed-Loop Materials Discovery and Biomedical Translation [0.30495228237759914]
  AIMBio is a conceptual framework for an AI-native, FAIR, and governance-aware decision layer.<n>It links materials provenance, biomedical context, knowledge graphs, uncertainty-aware machine learning, and human-in-the-loop active learning.
  arXiv  Detail & Related papers  (2026-05-20T12:18:49Z)
• BioMiner: A Multi-modal System for Automated Mining of Protein-Ligand Bioactivity Data from Literature [53.894504720119805]
  We introduce BioMiner, a multi-modal extraction framework for bioactivity data extraction.<n>Within BioMiner, bioactivity semantics are inferred through direct reasoning, while chemical structures are resolved via a chemical-structure-grounded visual semantic reasoning paradigm.<n>For rigorous evaluation and method development, we establish a benchmark comprising 16,457 bioactivity entries curated from 500 publications.
  arXiv  Detail & Related papers  (2026-04-23T10:11:56Z)
• Biomedical systems biology workflow orchestration and execution with PoSyMed [3.2613377085614417]
  PoSyMed is an open and modular platform for the controlled integration, composition, and execution of bioinformatics tools and tools.<n>PoSyMed combines a backend-centered platform architecture with formal tool descriptions, controlled container-based build and execution processes, persistent workflow state, and a dialogue-based user interface.
  arXiv  Detail & Related papers  (2026-04-21T20:20:58Z)
• Simple Agents Outperform Experts in Biomedical Imaging Workflow Optimization [69.36509281190662]
  Adapting production-level computer vision tools to bespoke scientific datasets is a critical "last mile" bottleneck.<n>We consider using AI agents to automate this manual coding, and focus on the open question of optimal agent design.<n>We demonstrate that a simple agent framework consistently generates adaptation code that outperforms human-expert solutions.
  arXiv  Detail & Related papers  (2025-12-02T18:42:26Z)
• BioinfoMCP: A Unified Platform Enabling MCP Interfaces in Agentic Bioinformatics [0.4500306327865278]
  BioinfoMCP enables natural-language interaction with sophisticated bioinformatics analyses without requiring extensive programming expertise.<n>We present a platform of 38 MCP-converted bioinformatics tools, extensively validated to show that 94.7% successfully executed complex interfaces across three widely used AI-agent platforms.
  arXiv  Detail & Related papers  (2025-10-02T15:47:59Z)
• BioAgents: Democratizing Bioinformatics Analysis with Multi-Agent Systems [6.668992155393883]
  We propose a multi-agent system built on small language models, fine-tuned on bioinformatics data, and enhanced with retrieval augmented generation (RAG)<n>Our system, BioAgents, enables local operation and personalization using proprietary data.<n>We observe performance comparable to human experts on conceptual genomics tasks, and suggest next steps to enhance code generation capabilities.
  arXiv  Detail & Related papers  (2025-01-10T19:30:59Z)
• Language Model Powered Digital Biology with BRAD [5.309032614374711]
  Large Language Models (LLMs) are well-suited for unstructured integration.<n>We present a prototype Bioinformatics Retrieval Augmented Digital assistant (BRAD)
  arXiv  Detail & Related papers  (2024-09-04T16:43:14Z)
• BioDiscoveryAgent: An AI Agent for Designing Genetic Perturbation Experiments [112.25067497985447]
  We introduce BioDiscoveryAgent, an agent that designs new experiments, reasons about their outcomes, and efficiently navigates the hypothesis space to reach desired solutions.<n>BioDiscoveryAgent can uniquely design new experiments without the need to train a machine learning model.<n>It achieves an average of 21% improvement in predicting relevant genetic perturbations across six datasets.
  arXiv  Detail & Related papers  (2024-05-27T19:57:17Z)
• An Evaluation of Large Language Models in Bioinformatics Research [52.100233156012756]
  We study the performance of large language models (LLMs) on a wide spectrum of crucial bioinformatics tasks. These tasks include the identification of potential coding regions, extraction of named entities for genes and proteins, detection of antimicrobial and anti-cancer peptides, molecular optimization, and resolution of educational bioinformatics problems. Our findings indicate that, given appropriate prompts, LLMs like GPT variants can successfully handle most of these tasks.
  arXiv  Detail & Related papers  (2024-02-21T11:27:31Z)
• Diversifying Knowledge Enhancement of Biomedical Language Models using Adapter Modules and Knowledge Graphs [54.223394825528665]
  We develop an approach that uses lightweight adapter modules to inject structured biomedical knowledge into pre-trained language models. We use two large KGs, the biomedical knowledge system UMLS and the novel biochemical OntoChem, with two prominent biomedical PLMs, PubMedBERT and BioLinkBERT. We show that our methodology leads to performance improvements in several instances while keeping requirements in computing power low.
  arXiv  Detail & Related papers  (2023-12-21T14:26:57Z)
• BiomedGPT: A Generalist Vision-Language Foundation Model for Diverse Biomedical Tasks [68.39821375903591]
  Generalist AI holds the potential to address limitations due to its versatility in interpreting different data types. Here, we propose BiomedGPT, the first open-source and lightweight vision-language foundation model.
  arXiv  Detail & Related papers  (2023-05-26T17:14:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.