# Reasoning Under Pressure: How do Training Incentives Influence Chain-of-Thought Monitorability?

arXiv: https://arxiv.org/abs/2512.00218 · HTML: https://mlsanity.com/paper/2512.00218/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Placed in Prompting and chain-of-thought reasoning, one of 17 directions in LLM reasoning.
- Builds on 27 of its 37 references that are in the map.
- First posted on arXiv 28 Nov 2025.

## Placed in

- LLM reasoning / [Prompting and chain-of-thought reasoning](https://mlsanity.com/lr/prompting-and-chain-of-thought-reasoning/)

## Builds on (most cited first, 27 of 27)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [OpenAI o1 System Card](https://mlsanity.com/paper/2412.16720/) (2024)
- [Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting](https://mlsanity.com/paper/2305.04388/) (2023)
- [Solving math word problems with process- and outcome-based feedback](https://mlsanity.com/paper/2211.14275/) (2022)
- [Measuring Faithfulness in Chain-of-Thought Reasoning](https://mlsanity.com/paper/2307.13702/) (2023)
- [Reasoning Models Don't Always Say What They Think](https://mlsanity.com/paper/2505.05410/) (2025)
- [Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation](https://mlsanity.com/paper/2503.11926/) (2025)
- [Alignment faking in large language models](https://mlsanity.com/paper/2412.14093/) (2024)
- [Reinforcement Learning for Reasoning in Large Language Models with One Training Example](https://mlsanity.com/paper/2504.20571/) (2025)
- [Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models](https://mlsanity.com/paper/2501.09686/) (2025)
- [Frontier Models are Capable of In-context Scheming](https://mlsanity.com/paper/2412.04984/) (2024)
- [Rewarding Progress: Scaling Automated Process Verifiers for LLM Reasoning](https://mlsanity.com/paper/2410.08146/) (2024)
- [Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety](https://mlsanity.com/paper/2507.11473/) (2025)
- [Training Language Models to Reason Efficiently](https://mlsanity.com/paper/2502.04463/) (2025)
- [Chain-of-Thought Reasoning In The Wild Is Not Always Faithful](https://mlsanity.com/paper/2503.08679/) (2025)
- [When Chain of Thought is Necessary, Language Models Struggle to Evade Monitors](https://mlsanity.com/paper/2507.05246/) (2025)
- [Stress Testing Deliberative Alignment for Anti-Scheming Training](https://mlsanity.com/paper/2509.15541/) (2025)
- [Don't Overthink it. Preferring Shorter Thinking Chains for Improved LLM Reasoning](https://mlsanity.com/paper/2505.17813/) (2025)
- [Are DeepSeek R1 And Other Reasoning Models More Faithful?](https://mlsanity.com/paper/2501.08156/) (2025)
- [SHADE-Arena: Evaluating Sabotage and Monitoring in LLM Agents](https://mlsanity.com/paper/2506.15740/) (2025)
- [Eliciting Latent Knowledge from Quirky Language Models](https://mlsanity.com/paper/2312.01037/) (2023)
- [CoT Red-Handed: Stress Testing Chain-of-Thought Monitoring](https://mlsanity.com/paper/2505.23575/) (2025)
- [All Code, No Thought: Current Language Models Struggle to Reason in Ciphered Language](https://mlsanity.com/paper/2510.09714/) (2025)
- [Benchmarks for Detecting Measurement Tampering](https://mlsanity.com/paper/2308.15605/) (2023)

## Built on by (most cited first, 9 of 9)

- [Aligned, Orthogonal or In-conflict: When can we safely optimize Chain-of-Thought?](https://mlsanity.com/paper/2603.30036/) (2026)
- [Monitorability as a Free Gift: How RLVR Spontaneously Aligns Reasoning](https://mlsanity.com/paper/2602.03978/) (2026)
- [When Reasoning Traces Become Performative: Step-Level Evidence that Chain-of-Thought Is an Imperfect Oversight Channel](https://mlsanity.com/paper/2605.11746/) (2026)
- [Length Penalties Make Chain-of-Thought Less Monitorable](https://mlsanity.com/paper/2607.09786/) (2026)
- [Corrupt Plans, Clean Traces: Evading Chain-of-Thought Monitoring with Plan Injection](https://mlsanity.com/paper/2609.15989/) (2026)
- [Monitor Jailbreaking: Evading Chain-of-Thought Monitoring Without Encoded Reasoning](https://mlsanity.com/paper/2609.31121/) (2026)
- [When Do Models Admit They Are Wrong? Failure Disclosure Is Unstable Under Reinforcement Learning](https://mlsanity.com/paper/2609.33220/) (2026)
- [A Near-Zero Monitor Readout Is Not Evidence of Behavioral Control](https://mlsanity.com/paper/2610.03458/) (2026)
- [Efficient Reasoning Training Does Not Always Harm CoT Faithfulness and Monitorability](https://mlsanity.com/paper/2610.03509/) (2026)

## Abstract (arXiv)

AI systems that output their reasoning in natural language offer an opportunity for safety -- we can 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 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.