Long-form video reasoning remains a major challenge for Video Large Language Models (Video LLMs), as static uniform frame sampling leads to information dilution and obscures critical evidence. Furthermore, existing pixel-space video reasoning agents, which are designed to actively interact with the video to acquire new visual information, remain suboptimal due to their lack of rigorous reward mechanisms to enforce evidence purity and their inability to perform temporal information supplementation beyond pre-sampled frames. To address this critical gap, we propose a novel evidence-prioritized adaptive framework built upon our core philosophy: "Select Less, Reason More." Our core contribution is the evidence-aware reinforcement learning (EARL) framework, which transforms the model into an active interrogator of evidence. EARL is precisely engineered to dynamically select the most relevant frames and, crucially, to perform localized re-sampling around the selected key frames to access fine-grained temporal detail. Extensive experiments on five demanding video reasoning benchmarks demonstrate that our EARL-trained model achieves new state-of-the-art among open-source Video LLMs, simultaneously learning an effective and high-purity visual evidence selection policy. Impressively, our 7B model achieves 59.8% on LongVideoBench, 69.0% on MVBench and 64.9% on VideoMME. These results highlight the importance of prioritizing evidence purity and the effectiveness of our framework.
ChemVLR: Prioritizing Reasoning in Perception for Chemical Vision-Language Understanding
The Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所复杂系统认知与决策智能重点实验室);School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院)
Exploring the Necessity of Reasoning in LLM-based Agent Scenarios
Huazhong University of Science and Technology(华中科技大学);Universiti Malaya(马来亚大学);Wuhan University of Technology(武汉理工大学);Duke University(杜克大学);Lehigh University(理海大学)
Traceable Evidence Enhanced Visual Grounded Reasoning: Evaluation and Methodology
New Laboratory of Pattern Recognition (NLPR), State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA)(中国科学院自动化研究所模式识别新实验室,多模态人工智能系统国家重点实验室,中国科学院)
Towards Efficient Multimodal Unified Reasoning Model via Model Merging
Beijing University of Posts and Telecommunications(北京邮电大学);Nanyang Technological University(南洋理工大学);Beijing Key Laboratory of Network System and Network Culture(北京网络系统与网络文化重点实验室);Key Laboratory of Interactive Technology and Experience System, Ministry of Culture and Tourism(文化和旅游部交互技术与体验系统重点实验室);Zhongguancun Academy, Beijing, China(中关村学院,北京,中国)
Can MLLMs Read Students' Minds? Unpacking Multimodal Error Analysis in Handwritten Math
Lehigh University(里海大学);Squirrel Ai Learning(松鼠AI学习);Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);Michigan State University(密歇根州立大学)
Beyond Access: Guided LLM Scaffolding for Independent Learning in Undergraduate Statistics
School of Electrical and Computer Engineering, University of Tehran, Iran(伊朗塔里哈大学电气与计算机工程学院);Tehran Institute for Advanced Studies, Khatam University, Iran(伊朗卡塔姆大学泰赫兰高级研究院)
Context-Aware Mapping of 2D Drawing Annotations to 3D CAD Features Using LLM-Assisted Reasoning for Manufacturing Automation
Singapore Institute of Manufacturing Technology (SIMTech), A*STAR, Singapore(新加坡制造技术研究所);Advanced Remanufacturing and Technology Centre (ARTC), A*STAR, Singapore(先进再制造与技术中心);School of Mechanical and Aerospace Engineering, Nanyang Technological University(机械与航空航天工程学院)