Multi-hopLLMsRetrievalMedical QABioCreative

Agentic and non-agentic multi-hop medical question answering

Built three multi-hop QA systems combining open-source LLMs with Wikipedia and PubMed retrieval, then compared agentic and controlled non-agentic workflows.

2025-08-141 min read

Overview

How do agentic and non-agentic multi-hop pipelines differ in medical QA accuracy, evidence use, and reliability?

System design

  • Developed three multi-hop systems combining open-source LLMs with Wikipedia and PubMed retrieval
  • Implemented an agentic workflow with smolagents and Qwen2.5-Coder-32B
  • Built controlled non-agentic pipelines for evidence retrieval, reranking, and answer extraction
  • Compared short-answer accuracy, evidence use, and reliability under the same evaluation setup

Results

  • Published the results at BioCreative IX / IJCAI 2025
  • Identified the best-performing retrieval configuration for the development set
  • Produced a side-by-side analysis framework for agentic vs non-agentic system behavior