Metraipolis › archive › dc_c435e4187ea2

Who May Overrule the Agent? Evidence-Gated Authority in LLM Review Institutions — arXiv:2611.05390

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.05390
License (as archived)
CC0-1.0
Archived
2026-11-05T18:16:23.299Z
SHA-256 of the archived text
fb285ea3b927761a989a03e2ec1f2c27c21cb65c190c6f6bf5502ddb2b19d7ab
Stable URL of this page
https://metraipolis.com/documento/dc_c435e4187ea2

How to cite

Who May Overrule the Agent? Evidence-Gated Authority in LLM Review Institutions — arXiv:2611.05390 — arXiv (en), https://arxiv.org/abs/2611.05390 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c435e4187ea2 (Metraipolis archive dc_c435e4187ea2, sha256 fb285ea3b927761a989a03e2ec1f2c27c21cb65c190c6f6bf5502ddb2b19d7ab)
BibTeX
@misc{dcc435e4187ea2,
  title = {Who May Overrule the Agent? Evidence-Gated Authority in LLM Review Institutions — arXiv:2611.05390},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.05390},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c435e4187ea2; sha256 fb285ea3b927761a989a03e2ec1f2c27c21cb65c190c6f6bf5502ddb2b19d7ab},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.05390. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Multi-agent language-model systems often add a reviewer to improve an upstream agent's decision. Yet a reviewer can both repair errors and replace decisions that were already correct. We study this as a problem of institutional jurisdiction: conditional on the same proposal, task information, model, and review output, when is the reviewer authorized to make its recommendation binding? We compare broad override authority with an evidence gate that permits replacement only after the reviewer produces a mechanically valid record of a binding-constraint violation and a compliant repair. Across two locally run open-weight models, 96 spatial-policy tasks, and a 96-task portfolio-transfer benchmark, the gate sharply reduces corruption of correct proposals while retaining most repairs of violations. The directions of this tradeoff are partly implied by the rule; its magnitude depends on reviewer transitions and upstream proposal states. A prospective validation then gives the reviewer an explicit choice to retain, replace, or escalate. This eliminates correct-proposal corruption for Qwen, but Mistral still replaces all 48 correct proposals; Qwen also declines every welfare-only repair that Mistral frequently attempts. Thus interface design changes reviewer behavior but is not a model-independent safeguard. The result is not that restricted review is universally better. It is that reviewer competence, action interface, and binding jurisdiction jointly determine both the correction domain and the corruption surface.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Multiagent Systems (cs.MA).
Pagina del lavoro: https://arxiv.org/abs/2611.05390 — 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 2026-11-05T18:10:09.309Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).