arXiv cs.CL· Yao Huang, Yifan Wang, Yitong Sun, Yichi Zhang, Yinpeng Dong·· 12 小时前AI 评分42
TraceMRT：针对隐蔽失准的思维链监控压力测试
Stress Testing Chain-of-Thought Monitoring Against Covert Misalignment
AI 导读
研究者提出 TraceMRT，一个自动化的轨迹级监控红队框架，将侧任务重构为主任务的连贯子目标，通过黑盒攻击发现 GPT-5.2 和 Claude-4.5 等顶尖监控模型仍存在显著漏洞。为此提出贝叶斯轨迹监控框架，融合全局上下文与局部片段证据检测隐蔽失准，达到 0.91 AUC 和 0.74 TPR@FPR=0.05。
正文 · 原文
Abstract:As LLM agents advance rapidly in autonomy, the risk of hidden objectives that bypass safety constraints becomes increasingly plausible. Chain-of-thought (CoT) monitoring offers a key control mechanism by reading the agent's reasoning and flagging misalignment before it materializes into action, yet its reliability depends on the realism of the red-team it is stress-tested against. Existing red-teaming efforts rely on shared templates, such as casting a side task as a prerequisite, which treat the side objective as an exogenous insertion and leave task-specific, contextually grounded evasions underexplored. We therefore ask: How robust is CoT monitoring against agents that strategically conceal misalignment? To answer this, we introduce TraceMRT, an automated Trace-level Monitor Red-Teaming framework that reframes the side task as a coherent sub-goal of the primary task and searches trace-shaping strategies whose induced trajectories complete the misaligned objective while reading as natural execution. Through black-box attacks on state-of-the-art monitors such as GPT-5.2 and Claude-4.5, we reveal substantial vulnerabilities even in top models. To counter these vulnerabilities, we propose a Bayesian Trajectory Monitoring framework, integrating global context and local segment evidence to detect covert misalignment. Empirically, our method significantly consolidates monitor robustness with 0.91 AUC and 0.74 TPR@FPR=0.05.
| Comments: | Advances in Neural Information Processing Systems (NeurIPS), 2026. 51 pages, 8 figures |
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2611.07586 [cs.CL] |
| (or arXiv:2611.07586v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2611.07586 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yifan Wang [view email]
[v1]
Thu, 5 Nov 2026 07:39:01 UTC (1,162 KB)
来源：arXiv cs.CL · arxiv.org