← Back to all articles
arXiv cs.AIOctober 7, 2026

Penumbra: Sample-Efficient Adversarial Search for Regulatory Obligations

Excerpt

arXiv:2610.04693v1 Announce Type: new Abstract: Agents are entering finance, healthcare and law, sectors where a violation leaves no lexical signature and carries real penalties. Whether an omission is material, or a disclosure sufficient, depends on what the response left out. Probing such an obligation means finding responses one minimal edit from flipping compliance, and every probe costs a generation and two adjudications, so the binding constraint on regulatory red-teaming is sample efficie