Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2602.06034 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915815178108928 |
|---|---|
| author | Chen, Dongyang Wang, Chaoyang Su, Dezhao Xiao, Xi Zhang, Zeyu Xiong, Jing Li, Qing Shang, Yuzhang Kan, Shichao |
| author_facet | Chen, Dongyang Wang, Chaoyang Su, Dezhao Xiao, Xi Zhang, Zeyu Xiong, Jing Li, Qing Shang, Yuzhang Kan, Shichao |
| contents | 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 verification.To 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_06034 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | V-Retrver: Evidence-Driven Agentic Reasoning for Universal Multimodal Retrieval Chen, Dongyang Wang, Chaoyang Su, Dezhao Xiao, Xi Zhang, Zeyu Xiong, Jing Li, Qing Shang, Yuzhang Kan, Shichao Computer Vision and Pattern Recognition 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 verification.To 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. |
| title | V-Retrver: Evidence-Driven Agentic Reasoning for Universal Multimodal Retrieval |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2602.06034 |