arXiv · 2611.18637
ReVision: Selective Intrinsic Reasoning for Tool-Augmented, Reasoning-Intensive VQA
Abstract
External tools substantially expand what multimodal large language models (MLLMs) can retrieve and compute on reasoning-intensive visual questions, and aggregate accuracy typically improves when tools are available. Our empirical study across six VQA benchmarks shows that aggregate accuracy gains under tool access can coexist with answer reversals: questions answered correctly without tools but incorrectly with tools. Trajectory analysis reveals substantially shorter reasoning turns under tool access, suggesting a shift from intrinsic visual reasoning toward reliance on external outputs. We propose ReVision, a training-free test-time method that registers intrinsic reconsideration as an optional action alongside search and code execution. When invoked, a separate tool-free multimodal call re-examines the original image, integrates accumulated evidence, and returns a revised analysis. The MLLM chooses if and when to use it, without fixed reflection stages or paired rollouts. ReVision improves over standard tool use on all six benchmarks (1.28--7.51\%) and outperforms Dual-Rollout Combine on five, with reasoning-token use comparable to standard tool use.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Ningxin Pan, Guochen Yan, Jialong Wu, Wentao Zhang. 2026-10-14. ReVision: Selective Intrinsic Reasoning for Tool-Augmented, Reasoning-Intensive VQA. https://searcharxiv.com/abs/2611.18637
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.