# SSE-Bio: A Structured Self-Evolving Agent with Agentic Retrieval Policy for Multi-Hop Biomedical Reasoning

arXiv: https://arxiv.org/abs/2608.22132 · HTML: https://mlsanity.com/paper/2608.22132/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use.
- Builds on 20 of its 33 references that are in the map.
- First posted on arXiv 22 Aug 2026.

## Placed in

- LLM agents and tool use / [Medical and scientific domain agents](https://mlsanity.com/agents/medical-and-scientific-domain-agents/)

## Builds on (most cited first, 20 of 20)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs](https://mlsanity.com/paper/2412.18925/) (2024)
- [Constructing Datasets for Multi-hop Reading Comprehension Across Documents](https://mlsanity.com/paper/1710.06481/) (2017)
- [MAPoRL: Multi-Agent Post-Co-Training for Collaborative Large Language Models with Reinforcement Learning](https://mlsanity.com/paper/2502.18439/) (2025)
- [Isambard-AI: a leadership class supercomputer optimised specifically for Artificial Intelligence](https://mlsanity.com/paper/2410.11199/) (2024)
- [Improving Retrieval-Augmented Generation in Medicine with Iterative Follow-up Questions](https://mlsanity.com/paper/2408.00727/) (2024)
- [Knowledge Graph Embedding: A Survey from the Perspective of Representation Spaces](https://mlsanity.com/paper/2211.03536/) (2022)
- [Self-Evolving Multi-Agent Simulations for Realistic Clinical Interactions](https://mlsanity.com/paper/2503.22678/) (2025)
- [MDTeamGPT: A Self-Evolving LLM-based Multi-Agent Framework for Multi-Disciplinary Team Medical Consultation](https://mlsanity.com/paper/2503.13856/) (2025)
- [RARE: Retrieval-Augmented Reasoning Enhancement for Large Language Models](https://mlsanity.com/paper/2412.02830/) (2024)
- [Leveraging Structured Information for Explainable Multi-hop Question Answering and Reasoning](https://mlsanity.com/paper/2311.03734/) (2023)
- [KGARevion: An AI Agent for Knowledge-Intensive Biomedical QA](https://mlsanity.com/paper/2410.04660/) (2024)
- [Agentic Medical Knowledge Graphs Enhance Medical Question Answering: Bridging the Gap Between LLMs and Evolving Medical Knowledge](https://mlsanity.com/paper/2502.13010/) (2025)
- [BioHopR: A Benchmark for Multi-Hop, Multi-Answer Reasoning in Biomedical Domain](https://mlsanity.com/paper/2505.22240/) (2025)
- [Trustworthy Medical Question Answering: An Evaluation-Centric Survey](https://mlsanity.com/paper/2506.03659/) (2025)
- [SEARL: Joint Optimization of Policy and Tool Graph Memory for Self-Evolving Agents](https://mlsanity.com/paper/2604.07791/) (2026)
- [Improve Rule Retrieval and Reasoning with Self-Induction and Relevance ReEstimate](https://mlsanity.com/paper/2505.10870/) (2025)
- [BiCA: Effective Biomedical Dense Retrieval with Citation-Aware Hard Negatives](https://mlsanity.com/paper/2511.08029/) (2025)
- [From Knowledge to Treatment: Large Language Model Assisted Biomedical Concept Representation for Drug Repurposing](https://mlsanity.com/paper/2510.12181/) (2025)

## Abstract (arXiv)

Biomedical multi-hop question answering (QA) requires models to connect evidence across intermediate entities such as diseases, drugs, proteins, and phenotypes. Existing agents typically rely on static retrieval workflows or coarse-grained prompt rewriting, which can lead to instruction drift when reasoning procedures need to be updated. We propose SSE-Bio, a structured self-evolving agent with an agentic retrieval policy for multi-hop biomedical reasoning. Instead of globally rewriting agent instructions, SSE-Bio maintains a structured state, selectively retrieves knowledge triplets and prior templates through a trainable proxy policy, and improves its reasoning memory through fine-grained template editing. To optimise retrieval decisions, we introduce a proxy-training strategy based on group relative policy optimization, where the proxy is improved through decision-contrastive groups over alternative retrieval choices. Experiments on three biomedical multi-hop QA benchmarks show that SSE-Bio consistently outperforms existing baselines, achieving an improvement of 6.56 absolute points over the strongest self-evolving baseline on BioHopR.