Unlocking the Unsolvable: Teacher-Guided Curriculum for Data-Efficient RLVR
Reinforcement Learning with Verifiable Rewards (RLVR) has shown remarkable success in improving the mathematical reasoning of large language models. Yet problems beyond the model's current capability, where rollouts uniformly fail and no learning signal is produced, are structurally wasted despite marking the most informative training frontier. We show that these otherwise-inert problems can be unlocked via teacher-guided curriculum learning: partial reasoning traces from a stronger model create a graded difficulty landscape, and a backward-chaining curriculum progressively withdraws guidance until the model solves problems unaided. Training on only 128 unsolvable problems matches or exce...
| Authors | Yukang Zhu, Zhen Han |
|---|---|
| Primary category | cs.CL |
| Published | 12 September 2026 |
| Last updated at source | 12 September 2026 |
Popularity, last 3 days
0 now. Counts as reported by the source, snapshotted daily by Silytics.
Connected in the knowledge graph
- yukangzhu/unlocking-the-unsolvableDataset · cited by
Models and datasets referencing this paper
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 19 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.