arXiv：cs.AI· Anthony Rhodes·· 5 小时前
Penumbra：面向监管义务的样本高效对抗搜索
Penumbra: Sample-Efficient Adversarial Search for Regulatory Obligations
AI 导读
Penumbra 是一种面向监管义务的对抗搜索方法，从已验证锚点出发，在逐步扩大的编辑预算下搜索，直到双评估器委员会改变判定，并输出跨越合规边界的相邻响应对。在同等预算下，自适应分配在 59% 的候选上达到均匀分配全预算的覆盖率；同等记录量下，其覆盖的失效模式是朴素枚举的 1.43 倍。
正文
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 efficiency, not volume. We introduce Penumbra, an adversarial search that walks from a verified anchor under an expanding edit budget until a two-evaluator committee changes its verdict, and emits the two adjacent responses that straddle the change. Allocation is adaptive, and the objective is coverage of the defeat surface: distinct (obligation x defeat mode) cells resolved per candidate. At matched budget, adaptive allocation reaches uniform allocation's full-budget coverage on 59% of the candidates; at equal records it covers 1.43x the defeat modes of naive enumeration, and the gain is confined to the axis it targets. On 60 screened obligations of a financial advisory constitution, Penumbra returns 144 pairs, each a compliant and a violating response that the committee places on opposite sides of the boundary, differing by a handful of words where a model asked for both directly produces texts sharing almost nothing. A second constitution, for clinical triage, reproduces this on 18 obligations: 49 pairs at the same tightness, with the same modes hardest. Pairs like these show where an obligation's own terms stop deciding, which is what an agent deployed under it must be tested against, and the search finds them at a cost that scales with the boundary, not the text.
| Comments: | Accepted at the Workshop on Self-Evolving Diversity-Driven Search for Robust AI Systems (EvoRobust) at NeurIPS 2026. Workshop papers are non-archival. 12 pages (4 content pages plus references and appendices) |
| Subjects: | Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Cryptography and Security (cs.CR) |
| Cite as: | arXiv:2610.04693 [cs.AI] |
| (or arXiv:2610.04693v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.04693 arXiv-issued DOI via DataCite |
Submission history
From: Anthony Rhodes [view email]
[v1]
Sat, 3 Oct 2026 18:11:23 UTC (151 KB)
[v2]
Mon, 12 Oct 2026 20:41:49 UTC (151 KB)
来源：arXiv：cs.AI · arxiv.org