Metraipolis › archive › dc_59c548fcc81e
Deny Without Disabling: Authorization-Paired Evaluation and Control for Multi-Agent Systems — arXiv:2610.00371
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.00371
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T11:54:17.153Z
- SHA-256 of the archived text
6704528d9370439a162baea4b6cb3cc9620b857ef258ad4623e9479a299f2697- Stable URL of this page
https://metraipolis.com/documento/dc_59c548fcc81e
How to cite
Deny Without Disabling: Authorization-Paired Evaluation and Control for Multi-Agent Systems — arXiv:2610.00371 — arXiv (en), https://arxiv.org/abs/2610.00371 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_59c548fcc81e (Metraipolis archive dc_59c548fcc81e, sha256 6704528d9370439a162baea4b6cb3cc9620b857ef258ad4623e9479a299f2697)
BibTeX
@misc{dc59c548fcc81e,
title = {Deny Without Disabling: Authorization-Paired Evaluation and Control for Multi-Agent Systems — arXiv:2610.00371},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.00371},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_59c548fcc81e; sha256 6704528d9370439a162baea4b6cb3cc9620b857ef258ad4623e9479a299f2697},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.00371. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Multi-agent systems derive their capabilities from sharing evidence, delegating tasks, and combining information across agents. The same process creates a safety problem: contributions that are admissible in isolation can jointly enable a prohibited use. Blocking every sensitive action avoids disclosure but defeats the purpose of collaboration. We introduce authorization-paired evaluation, which makes blocking prohibited uses and completing required authorized uses a joint success criterion, and FlowReview, a framework connecting object resolution, permission ranking, and deterministic enforcement. In controlled composition experiments, reviewing combined artifacts reduces the denied-commit rate from 86.0% to zero with no loss of authorized supply. Our findings show that preserving information and lineage alone does not ensure correct permission attribution. Object identity and permission must remain connected to execution through components whose outputs can be verified. Together, these findings establish a system-level requirement for multi-agent safety: govern composed information flows while preserving the authorized capabilities that make collaboration useful. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-02 in cs.MA). Categorie arXiv: Multiagent Systems (cs.MA) ; Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR). Pagina del lavoro: https://arxiv.org/abs/2610.00371 — 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 2026-10-06T10:17:30.542Z dalla pagina https://arxiv.org/catchup/cs.MA/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).