V-Retrver：面向通用多模态检索的证据驱动智能体推理

Computer Science > Computer Vision and Pattern Recognition arXiv:2602.06034 (cs) [Submitted on 5 Feb 2026 (v1), last revised 10 Sep 2026 (this version, v3)] Title:V-Retrver: Evidence-Driven Agentic Reasoning for Universal Multimodal Retrieval Authors:Dongyang Chen, Chaoyang Wang, Dezhao Su, Xi Xiao, Zeyu Zhang, Jing Xiong, Qing Li, Yuzhang Shang, Shichao Kan View a PDF of the paper titled V-Retrver: Evidence-Driven Agentic Reasoning for Universal Multimodal Retrieval, by Dongyang Chen and 8 other authors View PDF HTML (experimental) Abstract:Multimodal Large Language Models (MLLMs) have recently been applied to universal multimodal retrieval, where Chain-of-Thought (CoT) reasoning improves candidate reranking. However, existing approaches remain largely language-driven, relying on static visual encodings and lacking the ability to actively verify fine-grained visual evidence, which often leads to speculative reasoning in visually ambiguous cases. We propose V-Retrver, an evidence-driven retrieval framework that reformulates multimodal retrieval as an agentic reasoning process grounded in visual inspection. V-Retrver enables an MLLM to selectively acquire visual evidence during reasoning via external visual tools, performing a multimodal interleaved reasoning process that alternates between hypothesis generation and targeted visual this http URL train such an evidence-gathering retrieval agent, we adopt a curriculum-based learning strategy combining supervised reasoning activation, rejection-based refinement, and reinforcement learning with an evidence-aligned objective. Experiments across multiple multimodal retrieval benchmarks demonstrate consistent improvements in retrieval accuracy (with 23.0% improvements on average), perception-driven reasoning reliability, and generalization. Comments: Subjects: Computer Vision and Pattern Recognition (cs.CV) Cite as: arXiv:2602.06034 [cs.CV] (or arXiv:2602.06034v3 [cs.CV] for this version) https://doi.org/10.48550/arXiv.2602.06034 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Chaoyang Wang [view email] [v1] Thu, 5 Feb 2026 18:59:21 UTC (1,074 KB) [v2] Wed, 25 Feb 2026 10:30:35 UTC (1,074 KB) [v3] Thu, 10 Sep 2026 15:30:59 UTC (1,018 KB) Full-text links: Access Paper: View a PDF of the paper titled V-Retrver: Evidence-Driven Agentic Reasoning for Universal Multimodal Retrieval, by Dongyang Chen and 8 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.CV new | recent | 2026-02 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv (What is alphaXiv?) Links to Code Toggle CatalyzeX Code Finder for Papers (What is CatalyzeX?) DagsHub Toggle DagsHub (What is DagsHub?) GotitPub Toggle Gotit.pub (What is GotitPub?) Huggingface Toggle Hugging Face (What is Huggingface?) ScienceCast Toggle ScienceCast (What is ScienceCast?) Demos Demos Replicate Toggle Replicate (What is Replicate?) Spaces Toggle Hugging Face Spaces (What is Spaces?) Spaces Toggle TXYZ.AI (What is TXYZ.AI?) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower (What are Influence Flowers?) Core recommender toggle CORE Recommender (What is CORE?) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)