研究提议前沿AI开发商披露思维链可监控性指标

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.

本条情报归属 AITOP「论文」核心栏目，重点聚焦北美前沿实验室与硅谷科技巨头。在跨区域产业观察坐标中，该动态直接关联「AI 开发者工具链、Coding Agent 与工程化实践」研究主线，反映出当前技术演进与商业落地的最新风向。涉及核心实体与技术议题包括：Anthropic、OpenAI、Google DeepMind、AI安全，读者可通过下方标签进入对应专题页查阅历史脉络与关联对比。

信源核验说明：本文原始信息发布自一手权威信源「arXiv: Google DeepMind」（Tier-1 一手发布），具备高确定性参考价值。截至目前，全网已有 11 家独立信源对该事件进行交叉印证与跟进报道（含 Google DeepMind、Andrew Curran、OpenAI Blog 等），属于近期高关注度行业信号。