The paper introduces DyCPO, a co‑evolutionary framework that jointly optimizes token selection and adaptive counterfactual intervention for video reasoning. It builds a multi‑role dependence metric to balance visual exploration with answer‑relevance mining, suppressing filler tokens and spurious visual noise. By deriving counterfactual signals from the model’s own successful and failed rollouts, DyCPO enables self‑diagnostic analysis and co‑evolution of the optimization objective with the policy, leading to consistent performance gains on complex video reasoning benchmarks.
By Yudong Han, Yong Wang, Zaiquan Yang, Liang Lin, Chongyang Tao, Xiangxiang Chu, Liyuan Pan
arXiv:2609.36572v1 Announce Type: new
Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has been extended to Large Vision-Language Models (LVLMs), and perception-aware methods further e...
By Zhongan Bi, Kepeng Lin, Xuanang Gao, Yuhan Sun, Lianrun Zhang
arXiv:2610.16735v1 Announce Type: cross
Abstract: Multimodal reinforcement learning with verifiable rewards commonly assigns one sequence advantage to an entire response. This outcome-level signal di...
By Lihao Zheng, Zhenwei Shao, Zhou Yu, Yan Yang, Haoyi Sun, Qian Wang, Ning Mao, Pan Zhou
arXiv:2609.39168v1 Announce Type: new
Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has improved the reasoning capabilities of Multimodal Large Language Models (MLLMs), yet existing...
By Zhihan Zhang, Lizi Liao
arXiv:2606. 03937v1 Announce Type: new Abstract: While token-level entropy is commonly recognized as effective for credit assignment in text-only reinforcement learning with verifiable rewards (RLVR), it remains unclear whether this mechanism still holds in visual reasoning.
By Senjie Jin, Peixin Wang, Boyang Liu, Xiaoran Fan, Shuo Li, Zhiheng Xi, Jiazheng Zhang, Yuhao Zhou, Tao Gui, Qi Zhang, Xuanjing Huang
The paper introduces V‑Rubrics, a reinforcement‑learning framework that evaluates vision‑language model responses by breaking them into atomic propositions and scoring them on Visual Faithfulness, Reasoning Consistency, and Instruction Following. Using a fine‑tuned Qwen3‑VL‑8B‑Instruct model and a newly created 50K‑example V‑Rubrics dataset, the authors demonstrate that rubric‑based GRPO outperforms both a shared SFT baseline and an answer‑only GRPO, especially on knowledge‑oriented and visually grounded reasoning tasks.
By Shulin Tian, Minglun Li, Yuhao Dong, Hao Ding, Jiarui Yao, Haiwen Diao, Jingkang Yang, Hongyuan Zhu, Ziwei Liu
The paper introduces EASE, a method that enhances multimodal reinforcement learning with verifiable rewards (RLVR) by adding visual‑evidence process supervision. EASE transforms annotated evidence regions into smoothed visual‑token targets and uses them to guide attention during RL training, but only on high‑reward trajectories. Experiments on Qwen2.5‑VL‑7B, Qwen3‑VL‑4B, and Qwen3‑VL‑8B show that EASE improves average scores over DAPO by 2.5 to 3.1 points across perception, hallucination, visual math, and multimodal reasoning benchmarks, and diagnostics confirm better alignment of visual attention with annotated evidence.
By Ruina Hu, Chen Wang, Lai Wei, Jionghao Bai, Bin Yu, Weiran Huang, Kai Wang, Yue Wang
arXiv:2610.01973v1 Announce Type: new
Abstract: Reinforcement learning (RL) for video generation usually assigns one scalar reward to an entire sampled video. Yet a video is not uniformly flawed: som...
By Yifan Wang, Gordon Guocheng Qian, Yanyu Li, Anil Kag, Yun Fu
The paper introduces Activation Replay, a training‑free method that improves reasoning in post‑trained large multimodal models (LMMs) by replaying low‑entropy activations from the base model’s input context. It shows that Reinforcement Learning with Verifiable Rewards (RLVR) shifts low‑entropy activations and that modulating these activations enhances reasoning across tasks such as mathematics, visual agents, and video reasoning. Experiments demonstrate that Activation Replay outperforms alternatives like high‑entropy replay or direct cross‑model intervention, boosting Pass@K and broadening RLVR’s reasoning coverage.
By Yun Xing, Xiaobin Hu, Qingdong He, Jiangning Zhang, Shuicheng Yan, Shijian Lu, Yu-Gang Jiang
The paper investigates the faithfulness of visual information in multimodal chain-of-thought (MCoT) reasoning by large vision-language models (LVLMs). It shows that visual cues in MCoT are often inaccurate and largely ignored, as predictions change little when visual input is altered but significantly when textual input is changed. To improve visual faithfulness, the authors propose an annotation‑free Sufficient‑Component Cause Model (SCCM) that encourages the generation of minimal yet sufficient visual components, and demonstrate its effectiveness across fine‑grained perception and reasoning benchmarks.
By Zujing Liu, Junwen Pan, Qi She, Yuan Gao, Guisong Xia
VideoLVR introduces a method for multimodal large language models to maintain visual grounding during chain-of-thought reasoning by constructing latent visual evidence from local video regions at relevant moments. It uses a visual token prediction objective that unifies visual evidence reconstruction and text generation, allowing models to interleave text tokens with latent visual states. The approach is further extended with reinforcement learning, treating visual tokens as actions and optimizing policies with final-answer rewards, thereby improving video understanding without expanding the multimodal context.
By Shilong Li, Xingyuan Bu, Hao Shi, Yun Xing, Weixin Feng, Qiangpeng Yang, Shilei Wen
Complex visual question answering often requires vision-language models to think with images, i.e., actively acquire local visual evidence by zooming into informative regions of high-resolution images...