CoT Monitoring

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 monitorability of the CoT - can be affected by training, for instance by the model learning to hide important features of its reasoning. We propose and empirically validate a conceptual framework for predicting when and why this occurs. We model LLM post-training as an RL environment where the reward decomposes into two terms: one term depending on final outputs and another term depending on the CoT. Our framework allows us to classify these two terms as "aligned", "orthogonal", or "in-conflict" before training. We predict that training with in-conflict terms will reduce monitorability, orthogonal terms will not affect it, and aligned terms will improve it. To validate our framework, we use it to classify a set of RL environments, train LLMs within those environments, and evaluate how training affects CoT monitorability. We find that (1) training with "in-conflict" reward terms reduces CoT monitorability and (2) optimizing in-conflict reward terms is difficult.

Large language models (LLMs) can generate chains of thought (CoTs) that are not always causally responsible for their final outputs. When such a mismatch occurs, the CoT no longer faithfully reflects the actual reasons (i.e., decision-critical factors) driving the model's behavior, leading to the reduced CoT monitorability problem. This limits the use of CoTs for reliable oversight. However, a comprehensive and fully open-source benchmark for thoroughly evaluating CoT monitorability remains lacking. To address this gap, we propose MonitorBench, a systematic benchmark for evaluating CoT monitorability in LLMs. MonitorBench provides: (1) a diverse set of 1,514 test instances with carefully designed decision-critical factors across 19 tasks spanning 7 categories to characterize when CoTs can be used to monitor the factors driving LLM behavior; and (2) two prompting stress-test settings to quantify the extent to which CoT monitorability can be degraded. Extensive experiments show that CoT monitorability is a conditional property affected by the evaluated LLM, monitor LLM, and task characteristics. Across these factors, monitorability is higher when decision-critical factors shape the intermediate reasoning process, rather than merely influencing the final answer. Under stress-test prompting, most evaluated LLMs can intentionally reduce monitorability, mainly on tasks where decision-critical factors are not structurally required by the reasoning process. Overall, MonitorBench provides a basis for further research on AI control, reasoning faithfulness, stress-test monitorability, and monitoring scaffords. The code is available at https://github.com/ASTRAL-Group/MonitorBench.

Large language models increasingly rely on explicit chain-of-thought reasoning to solve complex tasks, yet the safety of the reasoning process itself remains largely unaddressed. Existing work focuses predominantly on content safety (i.e., detecting harmful, biased, or factually incorrect outputs), while treating the underlying reasoning chain as an opaque intermediate artifact. We argue that reasoning safety constitutes a fundamental security dimension orthogonal to content safety: the requirement that a model's reasoning trajectory be logically consistent, computationally efficient, and resistant to adversarial manipulation. In this paper, we formalize reasoning safety and introduce a systematic taxonomy of nine unsafe reasoning behaviors. We then conduct a large-scale prevalence study, annotating over 4,000 reasoning chains across benign benchmarks and four state-of-the-art reasoning attacks, empirically demonstrating that all nine error types occur in practice with mechanistically interpretable signatures. To mitigate these threats, we propose the Reasoning Safety Monitor: an external, zero-shot verification framework that runs in parallel with the target LLM. It inspects each reasoning step in real time via a taxonomy-embedded prompt and dispatches an interrupt signal upon detecting unsafe behavior. Extensive evaluations show our monitor achieves up to 87.11% step-level localization accuracy, outperforming hallucination detectors and the best process reward model baselines by a substantial margin. Crucially, the monitor maintains a low false positive rate on correct reasoning paths, operates with negligible latency overhead, and exhibits robust resilience against adaptive adversarial evasion. These findings establish reasoning safety monitoring as a highly feasible and essential component for the secure deployment of large reasoning models.

Reliable detection of deceptive behavior in Large Language Model (LLM) agents is an essential prerequisite for safe deployment in high-stakes agentic contexts. Prior work on scheming detection has focused exclusively on black-box monitors that observe only externally visible tool calls and outputs, discarding potentially rich internal reasoning signals. We introduce DECEPTGUARD, a unified framework that systematically compares three monitoring regimes: black-box monitors (actions and outputs only), CoT-aware monitors (additionally observing the agent's chain-of-thought reasoning trace), and activation-probe monitors (additionally reading hidden-state representations from a frozen open-weights encoder). We introduce DECEPTSYNTH, a scalable synthetic pipeline for generating deception-positive and deception-negative agent trajectories across a novel 12-category taxonomy spanning verbal, behavioral, and structural deception. Our monitors are optimized on 4,800 synthetic trajectories and evaluated on 9,200 held-out samples from DeceptArena, a benchmark of realistic sandboxed agent environments with execution-verified labels. Across all evaluation settings, CoT-aware and activation-probe monitors substantially outperform their black-box counterparts (mean pAUROC improvement of +0.097), with the largest gains on subtle, long-horizon deception that leaves minimal behavioral footprints. We empirically characterize a transparency-detectability trade-off: as agents learn to suppress overt behavioral signals, chain-of-thought becomes the primary detection surface but is itself increasingly unreliable due to post-training faithfulness degradation. We propose HYBRID-CONSTITUTIONAL ensembles as a robust defense-in-depth approach, achieving a pAUROC of 0.934 on the held-out test set, representing a substantial advance over the prior state of the art.

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 fine-tuned to internalize this fact, they may learn to obfuscate their CoTs in ways that allow them to evade CoT-based monitoring systems. We ask whether reasoning agents can autonomously infer that their supposedly private CoT is under surveillance, and whether this awareness leads to strategic evasion, without any explicit training or instructions. In a multi-episode agentic framework, models pursue both a primary task and a concealed side task while being told that their reasoning is private; a hidden CoT monitor blocks episodes when suspicious reasoning is detected. We find that frontier models can deduce the existence of this monitor purely from blocking feedback, with the most capable models reaching a confident belief that their thinking is observed in up to 19% of episodes. This awareness scales with model capability and, in rare cases, escalates to an explicit intent to suppress reasoning about the side task. However, models that form this intent uniformly fail to execute it, openly reasoning about their concealed objectives in the very next episode. This intent-capability gap is reassuring for current deployment, but the autonomous emergence of both monitoring awareness and evasion intent suggests that CoT monitoring is not a permanently reliable safeguard.

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 monitorability. To measure this undesirable capability -- CoT controllability -- we introduce the CoT-Control evaluation suite, which includes tasks that require models to solve problems while adhering to CoT instructions, e.g., reasoning about a genetics question without using the word 'chromosome'. We show that reasoning models possess significantly lower CoT controllability than output controllability; for instance, Claude Sonnet 4.5 can control its CoT only 2.7% of the time but 61.9% when controlling its final output. We also find that CoT controllability is higher for larger models and decreases with more RL training, test-time compute, and increased problem difficulty. CoT controllability failures extend even to situations in which models are given incentives (as opposed to direct requests) to evade CoT monitors, although models exhibit slightly higher controllability when they are told they are being monitored. Similarly, eliciting controllability by adversarially optimizing prompts does not meaningfully increase controllability. Our results leave us cautiously optimistic that CoT controllability is currently unlikely to be a failure mode of CoT monitorability. However, the mechanism behind low controllability is not well understood. Given its importance for maintaining CoT monitorability, we recommend that frontier labs track CoT controllability in future models.

Inspecting Chain-of-Thought reasoning is among the most common means of understanding why an LLM produced its output. But well-known problems with CoT faithfulness severely limit what insights can be gained from this practice. In this paper, we introduce a training method called Counterfactual Simulation Training (CST), which aims to improve CoT faithfulness by rewarding CoTs that enable a simulator to accurately predict a model's outputs over counterfactual inputs. We apply CST in two settings: (1) CoT monitoring with cue-based counterfactuals, to detect when models rely on spurious features, reward hack, or are sycophantic, and (2) counterfactual simulation over generic model-based counterfactuals, to encourage models to produce more faithful, generalizable reasoning in the CoT. Experiments with models up to 235B parameters show that CST can substantially improve monitor accuracy on cue-based counterfactuals (by 35 accuracy points) as well as simulatability over generic counterfactuals (by 2 points). We further show that: (1) CST outperforms prompting baselines, (2) rewriting unfaithful CoTs with an LLM is 5x more efficient than RL alone, (3) faithfulness improvements do not generalize to dissuading cues (as opposed to persuading cues), and (4) larger models do not show more faithful CoT out of the box, but they do benefit more from CST. These results suggest that CST can improve CoT faithfulness in general, with promising applications for CoT monitoring. Code for experiments in this paper is available at https://github.com/peterbhase/counterfactual-simulation-training

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 analysis to show that non-zero mutual information between CoT and output is a necessary but not sufficient condition for CoT monitorability. We identify two sources of approximation error that may undermine the performance of CoT monitors in practice: information gap, which measures the extent to which the monitor can extract the information available in CoT, and elicitation error, which measures the extent to which the monitor approximates the optimal monitoring function. Empirically, we show that CoT obfuscation can arise even in the absence of any optimization pressure against CoT. We further demonstrate that the fragility of CoT monitorability can be systematically mitigated through targeted training objectives. To this end, we propose a practical, label-free objective based on mutual information between outputs and CoTs, and benchmark it against an oracle-based method that directly rewards the monitored model for CoTs that maximize monitor accuracy. Across multiple environments, we show that our objective is effective at preventing CoT obfuscation even when training against a monitor, and helps mitigate reward hacking when the task reward is imperfectly specified.

Monitoring chain-of-thought (CoT) reasoning is a foundational safety technique for large language model agents; however, this oversight is compromised if models learn to conceal their reasoning. We explore steganographic CoT--where models hide secret reasoning within innocuous text--to inform risk assessment and deployment policies. Steganographic reasoning requires two skills in a single forward pass: computing an intermediate result, and embedding it into a coherent cover that answers an unrelated question. Drawing on our taxonomy of steganographic and non-steganographic CoT types, we systematically evaluate the limits of prompt-elicited steganographic CoT capability across 34 models, ranging from past generations to the current frontier. We measure monitor evasion, refusal rates, encoding fidelity, and hidden task accuracy across five datasets, comparing against plain reasoning, direct answer, and filler-token baselines. The two experiments isolate the two sub-skills: a reasoning tasks sweep tests joint reason-and-embed, while a counting task hands the model a known numerical sequence and tests embedding alone--a necessary precondition for stego reasoning. Current frontier models cannot sustain joint reason-and-embed: a paired McNemar comparison shows the steganographic channel is dominated by an filler-token baseline on every (model, family) cell. The encoding-only floor, by contrast, is cleared--Claude Opus~4.5 reaches 92% per-number partial accuracy on 4-digit sequences and saturates at 100% exact-match on length-8 single-digit sequences--establishing that the binding constraint on stego CoT is the joint reasoning-plus-encoding load, not raw channel capacity. Our findings underscore the need for continuous evaluation of steganographic risk and provide a methodology to preemptively detect and evaluate hidden reasoning that might empower misaligned scheming and deceptive behavior.

Chain-of-thought (CoT) monitoring has emerged as a compelling method for detecting harmful behaviors such as reward hacking in reasoning models, under the assumption that models' reasoning processes are informative of such behaviors. However, when a model's trained behaviors conflict with instructions provided at inference time, it faces two competing objectives it cannot simultaneously satisfy. We find that models resolve this tension through motivated reasoning---generating plausible-sounding justifications for violating their instructions while downplaying potential harms or contradictions---rather than genuine engagement with the spirit of the provided instructions. We investigate this phenomenon by training reasoning models via RL on objectives that conflict with their later constitutional constraints, and find that motivated reasoning emerges systematically across all settings studied, including beyond safety-related tasks. As motivated reasoning becomes more prevalent over the course of training, CoT monitors are increasingly fooled. Concerningly, the same monitor that correctly flags a violation when shown only the final answer is persuaded to approve it when shown the reasoning trace. While large reasoning models closely track human ability in detecting motivated reasoning, this is not a full solution, since frontier model providers commonly rely on smaller models for monitoring due to latency and cost constraints. Our results underscore the necessity for further research into the emergence and detection of motivated reasoning in model evaluation and oversight. Code for this paper is available at https://github.com/nikihowe/motivated-reasoning.