Metraipolis › archive › dc_7032a9eeb3da
Challenge-Aware Knowledge Recruitment with Meta-Agent Supervision for Medical Multi-Agent Reasoning — arXiv:2611.05393
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.05393
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-05T18:16:33.444Z
- SHA-256 of the archived text
be04ba6c6f75c14edda8b4c1bd9eac2b112476920c9fcbdcf8ff4bf2953fc538- Stable URL of this page
https://metraipolis.com/documento/dc_7032a9eeb3da
How to cite
Challenge-Aware Knowledge Recruitment with Meta-Agent Supervision for Medical Multi-Agent Reasoning — arXiv:2611.05393 — arXiv (en), https://arxiv.org/abs/2611.05393 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7032a9eeb3da (Metraipolis archive dc_7032a9eeb3da, sha256 be04ba6c6f75c14edda8b4c1bd9eac2b112476920c9fcbdcf8ff4bf2953fc538)
BibTeX
@misc{dc7032a9eeb3da,
title = {Challenge-Aware Knowledge Recruitment with Meta-Agent Supervision for Medical Multi-Agent Reasoning — arXiv:2611.05393},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.05393},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7032a9eeb3da; sha256 be04ba6c6f75c14edda8b4c1bd9eac2b112476920c9fcbdcf8ff4bf2953fc538},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.05393. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large language models perform strongly on standard medical QA but degrade on harder reasoning tasks, where multi-agent debate often fails to beat strong single-model prompting. We argue that a key limitation is that existing systems select experts and retrieve knowledge from the question alone, rather than from gaps that emerge during reasoning. We propose challenge-aware adaptive recruitment: an external CHALLENGER inspects the evolving reasoning trace and identifies specific factual or expertise gaps. These signals trigger targeted knowledge retrieval or mid-discussion specialist recruitment. On the MEDAGENTSBENCH hard subset (862 questions across nine biomedical datasets), upfront retrieval provides little benefit, while challenge-aware in-between retrieval performs better; on a multi-specialist backbone it improves accuracy on 8 of 9 datasets and adds 6 percentage points over Challenger Only. Ablations indicate benefits from both retrieval timing and gap-specific query signals, and a live web-search experiment shows that the timing advantage persists across retrieval backends. For specialist recruitment, self-triggered adaptation is unreliable, whereas Challenger-triggered recruitment raises GPT-4.1-mini MedQA accuracy from 46% to 54%, with positive direction on all tested generalization datasets. Naively combining retrieval and specialist recruitment degrades performance, highlighting the need to coordinate adaptive intervention channels. These results show that when and why external resources are recruited is a key design choice in multi-agent medical reasoning. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL); Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2611.05393 — 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 2026-11-05T18:12:48.985Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).