Metraipolis › archive › dc_0c17f676fc2a
Multi-Agent Screening: What Agreement and Acceptance Cannot Tell You — arXiv:2611.12705
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.12705
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-10T18:40:13.732Z
- SHA-256 of the archived text
915c82891d267983e1b3aee870163ec74843061c253795771e0e6c2092319096- Stable URL of this page
https://metraipolis.com/documento/dc_0c17f676fc2a
How to cite
Multi-Agent Screening: What Agreement and Acceptance Cannot Tell You — arXiv:2611.12705 — arXiv (en), https://arxiv.org/abs/2611.12705 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0c17f676fc2a (Metraipolis archive dc_0c17f676fc2a, sha256 915c82891d267983e1b3aee870163ec74843061c253795771e0e6c2092319096)
BibTeX
@misc{dc0c17f676fc2a,
title = {Multi-Agent Screening: What Agreement and Acceptance Cannot Tell You — arXiv:2611.12705},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.12705},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0c17f676fc2a; sha256 915c82891d267983e1b3aee870163ec74843061c253795771e0e6c2092319096},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.12705. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
When AI agents screen items for a costly human assessor, as in agentic search, e-discovery and AI reviewing of papers, only what they pass gets judged. We show what each kind of evidence can establish about their errors, even with unlimited data. Agreement shows that agents concur, not that they are right, however many there are. Acceptance by the assessor gives precision but only a lower bound on recall. Knowing which agents found which relevant items gives an upper bound on recall if agents' finds are not negatively correlated, and caps what one more agent can add if agents are interchangeable. Without assumptions about the agents, recall can be pinned down only by judging items they did not pass: a random sample of these estimates how many relevant items were missed, to any chosen accuracy, and the sample needed does not grow with the number of agents. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno). Categorie arXiv: Multiagent Systems (cs.MA) ; Artificial Intelligence (cs.AI); Information Retrieval (cs.IR). Pagina del lavoro: https://arxiv.org/abs/2611.12705 — 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 2026-11-10T18:37:22.457Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).