Agentic and Non-Agentic Multi-Hop Systems for Medical Question Answering
Bibliographic record
Abstract
Abstract This paper presents two systems developed for the MedHopQA Shared Task on multi-hop biomedical question answering. Our first system, Agentic-Qwen-Wikipedia, uses a lightweight agentic framework using SmolAgents to iteratively retrieve and reason over Wikipedia content via sub-query decomposition. Our second system, LLM-Qwen-Wikipedia-PubMed, offers a non-agentic, explicitly controlled pipeline that decomposes questions, retrieves evidence from both Wikipedia and PubMed, and synthesizes answers through a structured multi-hop process. The systems employ Qwen2.5-Coder-32B-Instruct-GPTQ-Int4 and Qwen-3-8B-AWQ, respectively. They are deployed efficiently using vLLM. The non-agentic system achieves higher performance on the shared task. This article is part of the Proceedings of the BioCreative IX Challenge and Workshop (BC9): Large Language Models for Clinical and Biomedical NLP at the International Joint Conference on Artificial Intelligence (IJCAI).
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.005 | 0.012 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.004 |
| Open science | 0.003 | 0.005 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.008 | 0.003 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".