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 which CoT faithfully reflects the underlying reasoning process, and hence the extent to which it can be usefully monitored, may be influenced by certain aspects of training. We investigate how different \emph{training incentives}, applied to a reasoning model, affect its monitorability. We introduce a novel methodology for measuring monitorability according to whether a monitor can predict a key latent variable using the model's reasoning. When controlling for accuracy, we do not find evidence for consistent effects from commonly used incentives (length penalties and KL regularisation), but we find that adversarial optimisation (penalising monitor accuracy) degrades monitor performance, while direct optimisation for monitorability does not reliably lead to improvements. Our code is available at https://github.com/QiyaoWei/reasoning-under-pressure.

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 measure two components of it: legibility (whether the reasoning can be followed by a human) and coverage (whether the CoT contains all the reasoning needed for a human to also produce the final output). We implement these metrics with an autorater prompt that enables any capable LLM to compute the legibility and coverage of existing CoTs. After sanity-checking our prompted autorater with synthetic CoT degradations, we apply it to several frontier models on challenging benchmarks, finding that they exhibit high monitorability. We present these metrics, including our complete autorater prompt, as a tool for developers to track how design decisions impact monitorability. While the exact prompt we share is still a preliminary version under ongoing development, we are sharing it now in the hopes that others in the community will find it useful. Our method helps measure the default monitorability of CoT - it should be seen as a complement, not a replacement, for the adversarial stress-testing needed to test robustness against deliberately evasive models.

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 faithfully, monitors can detect and mitigate harmful behaviors before undesirable outcomes occur. However, a key uncertainty is: Can models obfuscate their CoT in order to pursue hidden adversarial objectives while evading detection? To answer this question and thus stress-test CoT monitorability, we develop a composable and quantifiable taxonomy of prompts to elicit CoT obfuscation. We evaluate both internal CoT (reasoning traces) and external CoT (prompted reasoning in outputs) using toy tasks and more realistic environments in SHADE-Arena. We show that: (i) CoT monitoring performs accurately and efficiently without obfuscation pressure. (ii) Under strong obfuscation pressure, some models successfully complete adversarial tasks while evading detection. (iii) Models do not obfuscate their internal CoT as much as their external CoT (under prompt pressure). These results suggest that while CoT provides valuable oversight in benign settings, robust deployment requires model-specific stress-testing of monitorability.

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 some misbehavior to go unnoticed. Nevertheless, it shows promise and we recommend further research into CoT monitorability and investment in CoT monitoring alongside existing safety methods. Because CoT monitorability may be fragile, we recommend that frontier model developers consider the impact of development decisions on CoT monitorability.

Exploiting flaws or misspecifications in learning objectives, known as reward hacking in reinforcement learning (RL) settings, remains a critical failure mode in modern AI systems [1-3] and has led to agents exhibiting misaligned behaviors across many domains such as language modeling [4-6], control tasks [7-10], and recommendation systems [11-14]. The true objective function we wish to optimize is often hard to write down precisely, and so the challenge in creating capable and aligned systems largely lies in designing robust proxies that do not deviate in ways that a model may learn to exploit [3, 15]. This problem is not unique to machine learning systems but has also plagued human institutions [16-19]. For example, in 1902 the Hanoi government incentivized rat eradication by paying citizens for each rat tail they turned in; however, this policy backfired when people began farming rats specifically for their tails, which led to an even larger rat population [20]. Given that reward hacking is a problem even for humans, it seems unlikely that the issue will be solved for AI models by simply continuing to push the model intelligence frontier. In fact, enhancing an agent's capabilities may exacerbate the problem by better equipping it to discover and execute more complex and hard-to-monitor exploits [21, 22]. We have found this to be anecdotally true: as we have continued to scale RL training, agents have discovered more complex and hard-to-detect hacks. Thus far, the only general strategy for mitigating reward hacking is to manually monitor agents for unintended behavior, which is unlikely to scale as their outputs and actions grow more complex--possibly even superhuman--and become more widely used. The emerging generation of large language models (LLMs) [23] that are trained with reinforcement learning to reason in chain-of-thought (CoT) [24-26] offers a promising new avenue for monitoring.

Runtime Verification is a lightweight formal verification technique. It is used to verify at runtime whether the system under analysis behaves as expected. The expected behaviour is usually formally specified by means of properties, which are used to automatically synthesise monitors. A monitor is a device that, given a sequence of events representing a system execution, returns a verdict symbolising the satisfaction or violation of the formal property. Properties that can (resp. cannot) be verified at runtime by a monitor are called monitorable and non-monitorable, respectively. In this paper, we revise the notion of monitorability from a practical perspective, where we show how non-monitorable properties can still be used to generate partial monitors, which can partially check the properties. Finally, we present the implications both from a theoretical and practical perspectives.