[2604.09508] VISOR: Agentic Visual Retrieval-Augmented Generation via Iterative Search and Over-horizon Reasoning

Computer Science > Computer Vision and Pattern Recognition arXiv:2604.09508 (cs) [Submitted on 10 Apr 2026] Title:VISOR: Agentic Visual Retrieval-Augmented Generation via Iterative Search and Over-horizon Reasoning Authors:Yucheng Shen, Jiulong Wu, Jizhou Huang, Dawei Yin, Lingyong Yan, Min Cao View a PDF of the paper titled VISOR: Agentic Visual Retrieval-Augmented Generation via Iterative Search and Over-horizon Reasoning, by Yucheng Shen and 5 other authors View PDF HTML (experimental) Abstract:Visual Retrieval-Augmented Generation (VRAG) empowers Vision-Language Models to retrieve and reason over visually rich documents. To tackle complex queries requiring multi-step reasoning, agentic VRAG systems interleave reasoning with iterative retrieval.. However, existing agentic VRAG faces two critical bottlenecks. (1) Visual Evidence Sparsity: key evidence is scattered across pages yet processed in isolation, hindering cross-page reasoning; moreover, fine-grained intra-image evidence often requires precise visual actions, whose misuse degrades retrieval quality; (2) Search Drift in Long Horizons: the accumulation of visual tokens across retrieved pages dilutes context and causes cognitive overload, leading agents to deviate from their search objective. To address these challenges, we propose VISOR (Visual Retrieval-Augmented Generation via Iterative Search and Over-horizon Reasoning), a unified single-agent framework. VISOR features a structured Evidence Space for progressive...