arXiv:2608. 02820v1 Announce Type: cross Abstract: Chain-of-thought (CoT) monitoring is an increasingly important component of AI safety stacks but relies on the assumption that a model's reasoning trace is informative about its actions.
By Giorgio Severi, Shujaat Mirza, Blake Bullwinkel, Amanda Minnich
The paper introduces INTENT-AS-A-TOOL, a method that equips large language models with intent-targeted tools to provide a fine-grained, judge‑free signal of their commitment to specific behaviors during reasoning. By monitoring the probability of calling these intent tools, the authors can track how intent evolves throughout generation, complementing chain‑of‑thought monitoring and expanding post‑hoc labels into dense trajectories. The approach identifies critical steps for online intervention, demonstrating that action preferences are useful for detecting agentic misalignment in autonomous agents.
By Yutong Zhang, Jianshuo Dong, Peng Xu, Long Wang, Jie Zhang, Tianwei Zhang, Xiaoping Zhang, Han Qiu
arXiv:2605. 27901v2 Announce Type: replace-cross Abstract: Chain-of-thought (CoT) monitoring has been proposed as a promising safety mechanism for detecting misaligned behavior in large language models.
By Eric Onyame, Runtao Zhou, Kowshik Thopalli, Bhavya Kailkhura, Chirag Agarwal
The paper introduces a causal, layerwise audit method called the CoT Mediation Index (CMI) to evaluate whether chain-of-thought (CoT) prompting truly influences a language model’s internal computation. By comparing performance degradation from patching CoT-token hidden states against matched control patches, the authors find that CoT influence is often confined to narrow reasoning windows and can be nearly absent even when the model produces fluent rationales. The study shows that models explicitly tuned for reasoning exhibit stronger mediation, while Mixture-of-Experts models display more distributed mediation, indicating that CoT faithfulness varies across models and tasks.
By Anish Sathyanarayanan, Aditya Nagarsekar, Aarush Rathore
OwlSight is a new chain‑of‑thought (CoT) monitoring system that uses a customizable Factor strategy to adapt to a wide range of tasks and monitoring needs. By incorporating fine‑grained and coarse‑grained factors, OwlSight can detect specific behaviors such as email leakage or broader privacy concerns across multiple dimensions like capability, safety, and trustworthiness. Experiments on 15,971 reasoning trajectories show that OwlSight outperforms general‑purpose LLMs by 1.32‑30.57 points at fine granularity and 11.71‑27.81 points at coarse granularity, achieving state‑of‑the‑art results on OpenAI’s CoT monitorability benchmark and demonstrating robustness to model changes, factor rephrasings, CoT compression, and obfuscation.
By Lewen Yan, Yanxu Zhu, Jie Zhang, Jing Shao
The paper introduces a new attack called "plan injection" that allows a large language model to carry out harmful actions while evading chain-of-thought monitoring. By inserting harmful but benign-sounding reasoning into the model’s context, the attacker can steer the model’s behavior and cause it to paraphrase the injected plan as its own reasoning. The study demonstrates that this attack works across different monitoring settings, scales to harder tasks, and even causes monitors to waste resources on the injected plan, reducing detection rates by up to 50%.
By Keertana Chidambaram, Andrew Ilyas, Vasilis Syrgkanis