@article{vicurlstabilizingverifierindependentrlre, title = {VI-CuRL: Stabilizing Verifier-Independent RL Reasoning via Confidence-Guided Variance Reduction}, author = {Xin-Qiang Cai and Masashi Sugiyama}, year = {2026}, eprint = {2602.12579}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2602.12579}, }