OPD‑Aha is a privileged on‑policy distillation method that improves multimodal reasoning by reconstructing the distillation target from the teacher’s isolated visual preference instead of relying on fragile teacher‑student discrepancies. It suppresses continuations that contradict the image, encouraging students to interrupt flawed reasoning with reflection tokens such as "wait" and "actually." This approach leads to consistent improvements across fine‑grained perception and complex multimodal reasoning benchmarks.
By Chenhao Qiu, Dawei Li, Yechao Zhang, Lei Gong, Zhen Tan
arXiv:2606. 05718v1 Announce Type: cross Abstract: On-policy distillation (OPD) improves reasoning by training a student on trajectories sampled from its own policy under supervision from a teacher.
By Kanghui Tian, Siyuan Liu, Ziang Yan, Sheng Xia, Shuai Dong, Yi Wang
Privileged on-policy distillation improves multimodal reasoning by allowing a teacher to evaluate student trajectories using rich, training-only visual evidence. Both models score these trajectories w...
arXiv:2610.14939v1 Announce Type: new
Abstract: GRPO-style reinforcement learning has advanced vision-language reasoning, but its sequence-level rewards provide limited credit assignment for individu...
By Jiahe Feng
Visual tool use has emerged as a fundamental capability for multimodal agents to actively acquire evidence beyond a fixed image encoding. The prevailing recipe learns this capability from teacher-generated trajectories filtered for answer correctness, implicitly assuming that every successful demonstration provides effective supervision.
arXiv:2608. 08557v1 Announce Type: cross Abstract: Visual tool use has emerged as a fundamental capability for multimodal agents to actively acquire evidence beyond a fixed image encoding.
By Changhao Xiang, Shilin Zhang, Zheng Ma, Kanzhi Cheng, Ruize Ma, Yi Feng, Jianbing Zhang, Zhi Wang, Zhen Wu, Xinyu Dai, Lewei Lu
arXiv:2609.39120v1 Announce Type: new
Abstract: On-policy distillation (OPD) improves reasoning by providing token-level supervision from a teacher on a student's own trajectories. Existing methods p...
By Siyuan Liu, Kanghui Tian, Yue Duan, Yutao He, Shangdong Yang, Jian Zhang, Yinghuan Shi
The paper introduces Contrastive Vision On‑policy Distillation (CV‑OPD), a method that enhances on‑policy distillation for vision‑language models by adding a contrastive divergence loss and a discrepancy‑aware gating mechanism. CV‑OPD contrasts teacher distributions from positive and negative visual crops, forcing the student to rely on genuine visual evidence rather than shortcuts. Experiments on fine‑grained visual benchmarks show that CV‑OPD reduces shortcut learning and improves visual reasoning across existing VLMs.
By Haowei Wang, Hao Lin, Qi Zhu, Jiayi Ji, Deyi Ji, Liujuan Cao, Rongrong Ji
LEGO-OPD introduces a factorized teacher composition for multimodal on‑policy distillation, combining a Language Expert and a Grounding Expert into a single teacher distribution. By treating the language expert as a prior over tokens and the grounding expert as a visual likelihood that updates this prior, the method decouples language reasoning from visual grounding. Adaptive calibration further adjusts the influence of visual evidence at each decoding prefix, preventing over‑ or under‑supervision. Experiments with Qwen3 models demonstrate that LEGO‑OPD outperforms both single‑ and multi‑teacher baselines on multimodal and text‑only reasoning tasks, improving visual perception while preserving language reasoning.
By Jaeyun Shin, Hangeol Chang, Jong Chul Ye
CA-OPD is a confidence‑aware on‑policy distillation framework that improves structured visual prediction by using teacher confidence to selectively correct unreliable student transitions and gradually transfer rollout control to the student. The method aligns supervision with intervention decisions, providing direct cross‑entropy loss for corrected tokens and full predictive distribution for retained tokens. In a multi‑teacher setting for GUI grounding and OCR, CA‑OPD significantly outperforms the Qwen3.5‑0.8B baseline, achieving large gains on benchmarks such as ScreenSpot‑Pro and OCRBench‑v2 English.
By Menghao Li, Linjie Mu, Yin Wang, Haotian Hu, Yannian Gu, Lujiayi Xue, Fanyi Wang
VISTA is a method for active multimodal agents that internalizes collective visual experience via on‑policy distillation. It turns observations from multiple rollouts of the same input into shared supervision, using Collective Visual Experience Distillation (CVED) to organize observations with context and Heterogeneity‑Aware Policy Improvement (HAPI) to reinforce successful trajectories and guide learning from unsuccessful ones. The approach lets an experience‑conditioned teacher evaluate a student’s partial responses, enabling discoveries from one trajectory to inform others without altering the student’s original history, and achieves superior performance on fine‑grained perception and general reasoning tasks compared to comparable agents.
By Zheng Jiang, Houde Qian, Yiming Chen, Ling Li, Chaoyang Li, Yueqi Li, Yuxuan Liu, Lifeng Sun
arXiv:2608. 14144v1 Announce Type: cross Abstract: Visual on-policy distillation relies heavily on an informative teacher-student asymmetry, through either a larger, stronger teacher or privileged supervision, such as reference answers or ground-truth regions of interest.
By Yijiang Li, Yijun Liang, Yunjie Tian, Bingyang Wang, Ke Zhang, Zhenfei Yin, Di Fu, Philip Torr, Nuno Vasconcelos