- Rating
- 3
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper studied the RLVR data selection from the views of Reasoning Component Dependence (RCD) and Behavioral Entropy (BE). It first analyzed the different roles of training samples: low-BE high-RCD samples stabilize early optimization, mid-BE low-RCD samples provide the main performance gains, and high-BE low-RCD samples support late-stage exploration. Further, based on the above analysis, this paper proposed a stage-adaptive data selection strategy Called MechDS. Experiments on three models and three benchmarks show the effectiveness of MechDS.
Critical strengths
- The paper introduces an interesting perspective by incorporating mechanistic information into RLVR data selection. The analysis of high-RCD and low-RCD samples under different behavioral entropy levels is particularly interesting.
- The performance of the proposed method is promising. Specially, MechDS-Dynamic with a 10% selection budget surpasses DEPO with a 30% budget.
Critical weaknesses
- The generalizability of the stage-adaptive selection strategy deserves further investigation. Could the paper report the trained model on other domain benchmarks like LiveCodeBench and Crux?
- The design of the proposed method seems a little complex. Additional comparisons with alternative scheduling strategies could strengthen the justification for the proposed design.
Questions for authors
- The computational overhead of the proposed method should be reported and compared.