相关论文: CoT Red-Handed: Stress Testing Chain-of-Thought Mo…

While chain-of-thought (CoT) monitoring is an appealing AI safety defense, recent work on "unfaithfulness" has cast doubt on its reliability. These findings highlight an important failure mode, particularly when CoT acts as a post-hoc…

Recent findings suggest that misaligned models may exhibit deceptive behavior, raising concerns about output trustworthiness. Chain-of-thought (CoT) is a promising tool for alignment monitoring: when models articulate their reasoning…

Chain-of-thought (CoT) monitoring is one of the most promising tools we have for detecting model misbehavior, but its effectiveness depends on models faithfully externalizing their reasoning. Motivated by this vulnerability, we study…

Observability into the decision making of modern AI systems may be required to safely deploy increasingly capable agents. Monitoring the chain-of-thought (CoT) of today's reasoning models has proven effective for detecting misbehavior.…

As AI systems approach dangerous capability levels where inability safety cases become insufficient, we need alternative approaches to ensure safety. This paper presents a roadmap for constructing safety cases based on chain-of-thought…

AI systems that "think" in human language offer a unique opportunity for AI safety: we can monitor their chains of thought (CoT) for the intent to misbehave. Like all other known AI oversight methods, CoT monitoring is imperfect and allows…

Chain-of-thought (CoT) offers a potential boon for AI safety as it allows monitoring a model's CoT to try to understand its intentions and reasoning processes. However, the effectiveness of such monitoring hinges on CoTs faithfully…

Chain-of-thought (CoT) monitoring is proposed as a method for overseeing the internal reasoning of language-model agents. Prior work has shown that when models are explicitly informed that their reasoning is being monitored, or are…

Chain-of-thought (CoT) monitoring is a promising tool for detecting misbehaviors and understanding the motivations of modern reasoning models. However, if models can control what they verbalize in their CoT, it could undermine CoT…

Chain-of-thought (CoT) monitoring has been proposed as a promising safety mechanism for detecting misaligned behavior in large language models. However, its reliability remains largely unexplored beyond English and across diverse model…

While Chain-of-Thought (CoT) monitoring offers a unique opportunity for AI safety, this opportunity could be lost through shifts in training practices or model architecture. To help preserve monitorability, we propose a pragmatic way to…

Chain-of-thought (CoT) monitors are LLM-based systems that analyze reasoning traces to detect when outputs may exhibit attributes of interest, such as test-hacking behavior during code generation. In this paper, we use information-theoretic…

Mitigating reward hacking--where AI systems misbehave due to flaws or misspecifications in their learning objectives--remains a key challenge in constructing capable and aligned models. We show that we can monitor a frontier reasoning…

Detecting harmful AI actions is important as AI agents gain adoption. Chain-of-thought (CoT) monitoring is one method widely used to detect adversarial attacks and AI misalignment. However, attackers and misaligned models might evade CoT…

Chain-of-thought (CoT) outputs let us read a model's step-by-step reasoning. Since any long, serial reasoning process must pass through this textual trace, the quality of the CoT is a direct window into what the model is thinking. This…

AI systems that output their reasoning in natural language offer an opportunity for safety -- we can \emph{monitor} their chain of thought (CoT) for undesirable reasoning, such as the pursuit of harmful objectives. However, the extent to…

Chain-of-Thought (CoT) monitoring has emerged as a compelling method for detecting harmful behaviors such as reward hacking for reasoning models, under the assumption that models' reasoning processes are informative of such behaviors. In…

Chain-of-thought (CoT) traces are increasingly used both to improve language model capability and to audit model behavior, implicitly assuming that the visible trace remains synchronized with the computation that determines the answer. We…

OpenAI (2025) showed that training against a chain of thought (CoT) monitor can cause obfuscated CoTs, which contain bad behavior the monitor cannot detect. They proposed to keep CoTs monitorable by training only against output monitors…

Chain-of-Thought (CoT) monitoring, in which automated systems monitor the CoT of an LLM, is a promising approach for effectively overseeing AI systems. However, the extent to which a model's CoT helps us oversee the model - the…