Metraipolis › archive › dc_985d4f729fda
MediSkill-Evo: Process-Constrained Self-Evolution for Evidence-Grounded Clinical Interaction — arXiv:2608.23397
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.23397
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T07:41:56.642Z
- SHA-256 of the archived text
2318fa937a5cf6e91d1cd48a23350cb2e138b88d13c3c3efdf54975d84ece174- Stable URL of this page
https://metraipolis.com/documento/dc_985d4f729fda
How to cite
MediSkill-Evo: Process-Constrained Self-Evolution for Evidence-Grounded Clinical Interaction — arXiv:2608.23397 — arXiv (en), https://arxiv.org/abs/2608.23397 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_985d4f729fda (Metraipolis archive dc_985d4f729fda, sha256 2318fa937a5cf6e91d1cd48a23350cb2e138b88d13c3c3efdf54975d84ece174)
BibTeX
@misc{dc985d4f729fda,
title = {MediSkill-Evo: Process-Constrained Self-Evolution for Evidence-Grounded Clinical Interaction — arXiv:2608.23397},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.23397},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_985d4f729fda; sha256 2318fa937a5cf6e91d1cd48a23350cb2e138b88d13c3c3efdf54975d84ece174},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.23397. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Interactive clinical agents operate under partial observability, so reliable care depends on reaching the correct diagnosis through evidence-grounded, safe interactions. Yet existing agents struggle to convert experience into reusable process knowledge with explicit provenance and authority. To address this gap, we introduce MediSkill-Evo, which self-evolves governed process knowledge without fine-tuning the backbone. It realizes this self-evolution by updating clinical, process, symbolic, and visual knowledge in four typed banks under type-specific validation and scope rules. The Process-Constrained Preference Harness then turns validated knowledge into action by grounding candidates in evidence and prioritizing safer decisions. We evaluate on 300 MIMIC-IV-derived FullChain encounters, 180 hard-isolation conditions covering six process obligations, and 100 multimodal NEJM image-diagnosis cases. On Qwen FullChain, MediSkill-Evo improves diagnosis accuracy by 7.81% and treatment-intent coverage by 70.67% over the best-performing prior agent, while reducing critical failures by 43.04%. Under stress, it improves the stress-process composite by 7.77% and required-action completion by 12.41% over the best-performing agent for each metric, with stronger patient-fact, temporal-evidence, and triage-red-flag recovery and no controller-scored errors in unavailable-evidence, treatment, and triage safety checks. On multimodal NEJM diagnosis, MediSkill-Evo with optional MedSAM localization improves diagnosis accuracy by 2.56% and core score by 18.96% over the best-performing memory agent. Code is available at this https URL . Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-25 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.23397 — 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 2026-10-18T07:37:52.778Z 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).