IRDS: Interpretable RLVR Data Selection via Verifier-Coupled Sparse Autoencoder Coverage

ArXi:2605.28247v1 Announce Type: cross Reinforcement learning with verifiable rewards (RLVR) has become a key technique for en- hancing LLM reasoning, yet its data ineffi- ciency remains a major bottleneck. Existing methods address this problem only partially, each missing at least one of subset-level co- erage, verifier signal use, or interpretability. To address this gap, we present IRDS (Inter- pretable RLVR Data Selection), which selects