Multi-hopQwen2.5smolagentsRetrievalMedical QABioCreative

Agentic and non-agentic multi-hop medical question answering

Compared an agentic Qwen2.5 workflow with controlled Wikipedia and Wikipedia + PubMed pipelines to study how tool use and retrieval strategy affect answer quality.

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

  • Built an agentic Qwen2.5 workflow that iteratively searched Wikipedia
  • Let the model decide whether to continue gathering evidence or answer, with a 15-step cap
  • Built controlled Wikipedia and Wikipedia + PubMed comparison pipelines
  • Examined how tool use and retrieval strategy affected answer quality

Results

  • Published the results at BioCreative IX / IJCAI 2025
  • Produced a side-by-side analysis of agentic and non-agentic multi-hop system behavior