Shiao Xie, Siyu Chen, Jianwei Lv, Xiandong Li, Yujin Wang · 2026 · arXiv
DOI: 10.48550/arXiv.2610.26856 · open-access PDF
可验证奖励的多模式增强学习(RLVR)提供可靠的任务级监督,但为定位视觉推理中的错误提供了有限的指导。 基于政策的自我蒸(OPSD)补充了这种监督,由配备以证据为中心的视觉视觉视觉视图的特权教师进行密集的代币级纠正。
Machine translation (Meta M2M100); the English original follows.
Multimodal reinforcement learning with verifiable rewards (RLVR) provides reliable task-level supervision, yet offers limited guidance for localizing errors in visual reasoning. On-policy self-distillation (OPSD) complements this supervision with dense token-level corrections from a privileged teacher equipped with an evidence-centered visual view. However, the resulting corrections may conflate visual evidence with non-visual shifts induced by linguistic priors, response style, or the privileged view itself. We formalize this phenomenon as privileged-correction contamination: a token-level co
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.26856, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange