V-retrver: Evidence-driven Agentic Reasoning For Universal Multimodal Retrieval

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 verification.To train such an evidence-gathering retrieval agent, we adopt a curriculum-based learning strategy combining supervised reasoning activation, rejection-based refinement, and reinforc

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keychen2026v

Related papers

• Reasoning-augmented Representations For Multimodal Retrieval (2026)0.00
• TRACE: Task-adaptive Reasoning And Representation Learning For Universal Multimodal Retrieval (2026)0.00
• MARVEL: Multimodal Adaptive Reasoning-intensive Expand-rerank And Retrieval (2026)0.00
• Reasoning Guided Embeddings: Leveraging MLLM Reasoning For Improved Multimodal Retrieval (2025)0.00
• HIVE: Query, Hypothesize, Verify An LLM Framework For Multimodal Reasoning-intensive Retrieval (2026)0.00
• Indexing Multimodal Language Models For Large-scale Image Retrieval (2026)0.00
• Chain-of-thought Re-ranking For Image Retrieval Tasks (2025)1.81
• Multihaystack: Benchmarking Multimodal Retrieval And Reasoning Over 40K Images, Videos, And Documents (2026)0.00