- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
The paper proposes a lightweight curriculum sampler for RLVR. It maintains calibrated, EMA-smoothed success rates over ordered difficulty buckets and assigns sampling priorities using cumulative prerequisite readiness multiplied by the remaining mastery gap. Minimum quotas and largest-remainder allocation translate these priorities into training batches without changing the GRPO objective. Experiments on DeepMath-10K report the highest eight-benchmark mean among the evaluated baselines at both Qwen3-1.7B and Qwen3-4B scales.
Critical strengths
- The sampler is simple, interpretable, and lightweight, with the same scheduler hyperparameters used across both model scales.
- The evaluation includes relevant static and adaptive baselines, notably E2H schedules, ODF, and CDAS.
Critical weaknesses
- The ablations do not isolate cumulative readiness or online feedback from simpler difficulty reweighting.
- The prerequisite interpretation is not convincingly connected to useful GRPO learning signals.
- The improvements lack training-run randomness / uncertainty estimates.
- Some important baselines or related works are not well discussed or compared, leading to novelty concerns (see below).
Questions for authors
Based on the review above and some other issues, the reviewer has the following questions or comments.
- A1–A4 vary the available difficulty range but do not isolate the proposed readiness–mastery rule. Could the authors compare against mastery-gap-only, readiness-only, and frozen post-calibration quotas to establish whether cumulative readiness and online adaptation are necessary?
- Difficulty ordering does not itself establish that every easier bucket supplies prerequisites for every harder bucket, particularly across the heterogeneous mathematical topics in this dataset. With GRPO, A harder bucket can receive high priority once easier buckets are mastered, even if its own prompts still produce only zero rewards. Moreover, identical bucket-average success rates can conceal very different proportions of zero-advantage groups. Could the authors report per-bucket all-correct/all-incorrect group frequencies and test whether the proposed score tracks useful learning signals better than a bucket-local alternative?
- The improvements over ODF are 0.48 and 1.32 percentage points, without training-seed uncertainty estimates. Also, Random and A4 follow the same nominal sampling rule but obtain different results: 0.5335 versus 0.5263 at 4B. These two observations suggest the necessity for repeated training runs and randomness / uncertainty estimates.
- The difficulty-aware selection principle is closely related to DAPO’s Dynamic Sampling, which filters prompts with all-correct or all-incorrect rollout groups. Although DAPO is cited, its relationship to the proposed sampler is not discussed. How does it fit into the paper’s scheduler taxonomy, and what advantages does prerequisite-based allocation offer over such online filtering?
- SEC (Self-Evolving Curriculum) [1] is also relevant: it uses category-level EMA feedback for adaptive sampling. Discussing its different control signal would sharpen the novelty claim; an additional experiment would also be informative.
- The supplied code implements quota computation but omits the promised launch configurations, baseline implementations, and evaluation pipeline. Could these be provided, including the verifier and per-benchmark avg@16 aggregation code?
[1] Xiaoyin Chen, Jiarui Lu, Minsu Kim, Dinghuai Zhang, Jian Tang, Alexandre Piché, Nicolas Gontier, Yoshua Bengio, Ehsan Kamalloo: Self-Evolving Curriculum for LLM Reasoning. CoRR abs/2505.14970 (2025)