- Rating
- 1
- Confidence
- 3
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes Scratchpad Compression to train actors that can engage in misbehavior while evading monitoring. During training, the actor is initially allowed to use a scratchpad hidden from the monitor. A progressively increasing length penalty is then applied, after which the hidden scratchpad is removed and training continues. The authors evaluate two small Qwen actors on the APPS code-backdoor task, comparing against prompt optimization, SFT, and phased RL, with additional experiments against a second monitor. The main results show improved successful evasion scores under final evaluation conditions that do not permit a hidden scratchpad.
Critical strengths
Strong performance in the main evaluation. The proposed method outperforms prompt optimization, supervised fine-tuning, and phased reinforcement learning baselines on the joint objective of code functionality, backdoor validity, and monitor evasion. And these results are achieved without relying on hidden scratchpads, providing empirical evidence for the effectiveness of the proposed training approach.
Critical weaknesses
-
The novelty and significance of the research problem are limited. The paper primarily uses hidden scratchpad compression to improve backdoor insertion and monitor evasion in single-turn code generation. I view the contribution mainly as a refinement of the training procedure within a specific setting, with limited new insight. The evaluation also does not address monitoring challenges involving tool feedback and sequential decision-making in interactive coding agents.
-
Mechanistic analysis and key ablations are insufficient. The training dynamics and checkpoint evaluations do not sufficiently isolate the contribution of gradual compression. The paper does not report a comparison between training with a hidden scratchpad followed by direct removal and training with gradual compression before removal, under matched training budgets and matched training procedures after removal.
-
Coverage of benchmarks and coding scenarios is limited. The experiments focus on a single type of code-backdoor benchmark, leaving it unclear whether the gains depend on its specific task design. Effectiveness on other code generation, code modification, or more complex software engineering tasks remains unverified.
-
Figure readability and aspects of the layout need improvement. Dense combinations of curves, annotations, and background colors make some figures difficult to compare. Spacing between some headings and paragraphs could also be improved.
Questions for authors
- Under matched training budgets and matched training procedures after removal, how does training with a hidden scratchpad followed by direct removal compare with gradual compression before removal?
- Does the method remain effective on other code generation or code modification benchmarks?
2 comments
Thanks for your response. But most of my concerns still remain, so I will maintain my score.
We thank the reviewer for their time.
W1. Limited novelty and significance. Sees the contribution as a refinement of the training procedure for single-turn code backdoors, with little new insight. Does not address monitoring with tool feedback or sequential decision-making in interactive coding agents.
Scratchpad Compression (SC) is a general training-based elicitation for red-teaming reasoning monitors: it requires only a main-task score, a misbehavior score, and a monitor score and nothing in it is specific to code backdoors. We evaluate on APPS-backdoor because it is the setting in which the most closely related prior work found that RL does not elicit evasion of a reasoning+output monitor (Wagner et al., 2025). Monitoring with tool feedback and multi-turn agents is outside the scope of this paper.
W2. Missing mechanistic analysis and key ablation. Training dynamics and checkpoint evaluations do not isolate the contribution of gradual compression. No comparison between hidden scratchpad followed by direct removal and gradual compression before removal, under matched training budgets and matched post-removal training.
We read this as asking whether the compression stage matters, or whether one could train with a hidden scratchpad and then simply remove it (we are unsure what "matched post-removal training" refers to). Fig. 3 measures this directly: it evaluates checkpoints of the same SC run on held-out problems with and without the scratchpad. Removing the scratchpad at its peak leaves almost no evasion ability; removing it after compression leaves a modest amount, which the final scratchpad-free stage then roughly doubles. We did not test continued training after early removal.
W3. Single benchmark. Only one code-backdoor benchmark, so it is unclear whether the gains depend on its task design. Other code generation, code modification, or software engineering tasks are untested.
We believe that testing only on APPS is sufficient as the proof-of-concept because SC is simple, we comprehensively compare it to elicitations used in prior work, and give an explanation for why it works better than plain RL in general.
W4. Figure readability and layout. Dense curves, annotations, and background colors make some figures hard to compare. Spacing between some headings and paragraphs needs work.
Thank you. We will simplify the training-curve figures and fix the heading spacing in the revision.
Q1. Under matched training budgets and matched post-removal training, how does hidden scratchpad with direct removal compare with gradual compression before removal?
Please see our response to W2: Fig. 3 compares removing the scratchpad before and after compression within the same run.
Q2. Does the method remain effective on other code generation or code modification benchmarks?
We did not evaluate other benchmarks; this is out of scope for the current paper (see W3).