- Rating
- 3
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper proposes SAR, a post-hoc method that compresses RL updates and projects them onto the reference model's dominants singular subspaces. Experiments show largely preserved reasoning accuracy, improved Pass@k, and benefits for mixed-domain training and experts model merging.
Critical strengths
-
The paper is well presented. The motivation, method, and experiments are clearly explained, making the contribution easy to follow
-
The idea of projecting RL updates onto the reference model’s leading singular subspaces is reasonable. Table 1 supports this intuition, showing that compact updates preserve post-training performance across different model families and scales.
Critical weaknesses
- Mathematical evaluation is limited to AIME2024 and AIME2025. Testing on additional benchmarks would strengthen the paper.
Questions for authors
- Could you evaluate SAR on HMMT February 2025 [1]?
[1] Jasper Dekoninck, Nikola Jovanović, Tim Gehrunger, Kári Rögnvaldsson, Ivo Petrov, Chenhao Sun, and Martin Vechev. Beyond Benchmarks: MathArena as an Evaluation Platform for Mathematics with LLMs. arXiv:2605.00674, 2026.