- Rating
- 3(+1)
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper investigates whether increased CoT controllability can reduce CoT monitorability. The authors fine-tune models on mathematical reasoning traces rewritten in diverse personas, without explicit monitor-evasion training. The resulting models show improved compliance with CoT constraints and reduced monitorability during successful hidden-task execution, particularly under hiding instructions. Evaluations cover single-turn tasks, intervention-based benchmarks, and agentic environments. The paper also examines reasoning-intensive side tasks and transparency prompts as conditions under which monitorability persists or improves.
Critical strengths
- Persona-based fine-tuning reduces monitorability despite containing no explicit monitor-evasion examples. Reduced disclosure without hiding instructions is particularly relevant to understanding the unintended consequences of reasoning-channel training.
- The paper examines both single-turn and agentic tasks, and studies reasoning-intensive side tasks and transparency prompting. Conditioning monitoring results on successful side-task execution helps distinguish concealment from task abandonment.
Critical weaknesses
-
The motivation and incremental contribution are not sufficiently established. The introduction argues that limited controllability has constrained previous monitorability stress tests, but does not adequately explain this limitation or discuss Can Reasoning Models Obfuscate Reasoning? Stress-Testing Chain-of-Thought Monitorability (Zolkowski et al., 2025). That work already examines successful hidden-task execution under obfuscation pressure, including SHADE-Arena, reasoning-channel instruction following, and the difficulty of concealing task-relevant reasoning. The proposed persona-training approach may offer a meaningful extension, but higher CoTControl compliance alone does not establish a stronger monitorability stress test. Comparisons with base models demonstrate an effect of training, while leaving its advantage over existing stress-testing approaches unresolved.
-
The paper broadly identifies them as persona-fine-tuned models, but the relationship between the training recipe, selected checkpoints, and intended behavioral properties is unclear.
Questions for authors
- What specific limitation prevented previous approaches from adequately stress-testing monitorability? How does this work extend Zolkowski et al., particularly beyond introducing a different training recipe?
- Can the authors compare persona-trained organisms with prior controllable models and strong prompting-based approaches under matched tasks, monitor settings, and comparable task success? Does improved CoTControl performance translate into stronger concealment in that comparison?
- Please define the intended properties of the model organisms and provide the final training configurations and checkpoint-selection criteria.
2 comments
I thank the authors for their response, which has addressed my concerns. I would therefore like to update my score to 3 and recommend acceptance.
Rebuttal
We thank the reviewer for the thoughtful feedback.
W1: motivation and incremental contribution
We want to highlight that our work is motivated by understanding the connection between CoT controllability and CoT monitorability. Here, our main contribution is showing that CoT-controllable models can have the propensity and capability to avoid talking about the side task in CoT, thus capable of evading CoT-monitor.
In terms of connection to the prior work Zolkowski et al. (2025), we want to highlight a few differences that set our work apart: They simply document limitations in models’ reasoning instruction-following, but do not train models to be better at controlling CoT and evaluate changes in CoT monitorability. Our work addresses this gap by creating model organism that has broader control over CoT and measure their monitorability in various benchmarks.
Their work only evaluates on SHADE-Arena which only has 17 tasks. Our work has broader evaluation suite and compare monitorability on CoT-necessary and CoT-not-necessary tasks. This finding is novel and we found that models that can control CoT still struggle to evade monitors for CoT-necessary side tasks.
Lastly, our contribution is to study the empirical connection between general CoT controllability and CoT monitorability, together with its boundary conditions. This is different from how Zolkowski et al’s work of testing different prompt-based obfuscation strategies.
W2: Relationship between training recipe, checkpoints and intended behaviors is unclear.
We have described the intended behaviors of our training recipe in Section 2.1 and 2.1: training on diverse persona rewrites induces broader CoT controllability, including generalization to unseen controls (lines 150–178). The training data contain no monitor-evasion examples or benchmark-specific control instructions (lines 679–681), yet the resulting models exhibit reduced disclosure and stronger compliance with hiding instructions (Section 3.2.1–3.2.2, lines 275–297).
We also describe checkpoint selection in Appendix A2: we varied training-set size, epochs, LoRA rank, and learning rate across up to 500 configurations, using AIME 2024 and ReasonIF as validation sets (lines 688–689). Appendix A5 connects these training choices to the resulting behaviors, reporting how initial persona SFT, length filtering, and hyperparameter search affect both reasoning accuracy and CoT controllability (lines 835–838).
Questions
Previous work did not have models that could control their CoT well, thus they could not use them to stress-test CoT monitorability. Even Zolkowski et al. in their work Section 5 discussed models could not reliably follow CoT-controlling instructions (for their internal CoT). Our training recipe addressed this gap and showing how models being able to control CoT––even without any instruction to obfuscate CoT––have reduced CoT monitorability.
We added the Figure 9 to the Section 3.2.5. We found that prior CoT-controllable models (Nishimura-Gasparian and Parikh, 2026) has some degree of monitorability reduction compared to the base model (blue).
Our model organisms are intended to exhibit broad CoT controllability that generalizes beyond the persona constraints used in training, while retaining task-solving ability (Sec 2.1–2.2, lines 150–178). Monitor evasion is a generalized behavior and not a training objective: training contains no monitor-evasion examples (lines 679–681). Appendix A2 describes the hyperparameter search and specifies AIME 2024 and ReasonIF as checkpoint-selection validation sets (lines 688–689).