Metraipolis › archive › dc_05ffdfc2623e
SSE-Bio: A Structured Self-Evolving Agent with Agentic Retrieval Policy for Multi-Hop Biomedical Reasoning — arXiv:2608.22132
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.22132
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T07:42:41.737Z
- SHA-256 of the archived text
f880cd5ac5643ab9053b5d81f316c03a641c090c8e6b35ce3357b28f1567f579- Stable URL of this page
https://metraipolis.com/documento/dc_05ffdfc2623e
How to cite
SSE-Bio: A Structured Self-Evolving Agent with Agentic Retrieval Policy for Multi-Hop Biomedical Reasoning — arXiv:2608.22132 — arXiv (en), https://arxiv.org/abs/2608.22132 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_05ffdfc2623e (Metraipolis archive dc_05ffdfc2623e, sha256 f880cd5ac5643ab9053b5d81f316c03a641c090c8e6b35ce3357b28f1567f579)
BibTeX
@misc{dc05ffdfc2623e,
title = {SSE-Bio: A Structured Self-Evolving Agent with Agentic Retrieval Policy for Multi-Hop Biomedical Reasoning — arXiv:2608.22132},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.22132},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_05ffdfc2623e; sha256 f880cd5ac5643ab9053b5d81f316c03a641c090c8e6b35ce3357b28f1567f579},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.22132. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-25 in cs.AI). Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI); Computational Engineering, Finance, and Science (cs.CE). Pagina del lavoro: https://arxiv.org/abs/2608.22132 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-18T07:37:52.857Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).