Evidence record 13792 · automatically gathered

State-dependent error correlations shape voting thresholds in committees of AI agents

arXiv:2607.23931v1 Announce Type: new Abstract: The aggregation benefit of a committee of artificial intelligence (AI) agents comes from complementary information across members. Classical voting guarantees assume independent errors. Language-model errors often co-occur on the same cases. We combine Sah-Stiglitz screening with error dependence that can differ between good and bad cases. In a homogeneous exchangeable Gaussian-copula model, shared errors create a positive asymptotic error floor fo

Record details

Published: 28 July 2026
Source: arXiv cs.CY
Category: Research
Topics: Agents & autonomy
Retrieved: 28 July 2026

source-onlyevidence status

These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.

How to cite this record

ethics.ai (28 July 2026), “State-dependent error correlations shape voting thresholds in committees of AI agents,” evidence record 13792, https://ethics.ai/record/13792 (originally published by arXiv cs.CY).

JSON

Use and limitations

This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.