arXiv · 2611.12705
Multi-Agent Screening: What Agreement and Acceptance Cannot Tell You
Abstract
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.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Benjamin Chang, Dell Zhang. 2026-11-09. Multi-Agent Screening: What Agreement and Acceptance Cannot Tell You. https://searcharxiv.com/abs/2611.12705
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.