研究提议前沿AI开发商披露思维链可监控性指标
Transparency Disclosures for Chain-of-Thought Monitorability
Anthropic、OpenAI、DeepMind 三家的披露全被审了一遍，没有一家把五项CoT监控指标报齐。做AI安全或评估的人可以拿这份清单直接对照自家或客户的披露口径。
arXiv 上一项研究指出，思维链（CoT）监控正受到威胁，前沿AI开发商应定期披露五项指标，分别对应CoT监控依赖链条的五个环节。这五项指标覆盖第三方CoT访问权限与基础架构规格、CoT质量（自然性与忠实性）、监控有效性（检出率与能力提升）。第一项第三方访问与架构规格指标还是其余指标外部验证的基础。
研究审计了 Anthropic、OpenAI 和 Google DeepMind 三家的现有披露情况，结果显示没有任何一家开发商覆盖全部五项指标，但每项指标至少被一家前沿开发商报告过。由于目前的披露主要依赖开发商自评，作者建议开展跨开发商审计，采用比公开披露更深入的访问方式，例如在开发商内部工作的嵌入式评估者，或由独立验证组织（Independent Verification Organization）执行。
这项工作把AI安全讨论落到可量化的披露指标上，为监管机构和第三方审计提供了具体抓手。对关注CoT监控失效风险的企业和研究者来说，五指标框架可以直接作为评估开发商透明度的清单。
Transparency Disclosures for Chain-of-Thought Monitorability
Chain-of-thought (CoT) monitoring is one of the most valuable tools for monitoring advanced AI systems, but it is under threat. We argue that frontier AI developers should report specific indicators to make these threats trackable and to better facilitate coordination to preserve CoT monitorability. We identify five indicators that are both highly relevant and reasonably feasible to disclose, one for each link in a five-step chain on which CoT monitoring depends. The first, third-party CoT access and base architecture specifications, also underpins external verification of the rest. The others span CoT quality (naturalness and faithfulness) and monitoring effectiveness (detection and uplift). An audit of current disclosures by Anthropic, OpenAI, and Google DeepMind shows that no developer covers the full set, but that every indicator has been reported by at least one frontier developer. Because current disclosures rely largely on developers' own evaluations, we also recommend that a cross-developer audit be repeated with deeper access than public disclosures allow, either by embedded evaluators working within developers or by an Independent Verification Organization.
This report is categorized under AITOP's "Papers" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include Anthropic, OpenAI, Google DeepMind, AI安全.
Primary source verification: published directly by arXiv: Google DeepMind with first-party authority. Cross-source corroboration: 11 independent sources have covered this development (including Google DeepMind, Andrew Curran, OpenAI Blog), confirming industry-wide signal strength.
