ETCHR: Editing To Clarify and Harness Reasoning
2026-05-22 • Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionArtificial IntelligenceComputation and Language
AI summaryⓘ
The authors identify that while current models combining text and images can reason visually, they struggle when detailed focus or perspective changes are needed. They create a new approach called ETCHR, which uses a separate image editor guided by the question to improve the editing process and reasoning accuracy. ETCHR is trained in two steps to better mimic and enhance reasoning edits and works with various language-vision models without extra training. Their method improves performance on several visual reasoning tasks compared to previous techniques. This shows that separating image editing from understanding models helps make reasoning with images clearer and more effective.
Multimodal Large Language ModelsVisual reasoningImage editing modelsChain of thoughtReasoning imitationVision-language modelsFine-grained perceptionChart understandingLogic reasoning3D understanding
Authors
Beichen Zhang, Yuhong Liu, Jinsong Li, Yuhang Zang, Jiaqi Wang, Dahua Lin
Abstract
Multimodal Large Language Models have advanced visual reasoning, yet a purely textual chain of thought remains a bottleneck for questions that require fine-grained focus or view transformations. The ''think with images'' paradigm narrows this gap, but existing approaches are either constrained by fixed predefined toolkits or produce noisy intermediate images from unified multimodal methods. We pursue a third option: using a dedicated image editing model and decouple it with an understanding model. However, off-the-shelf image editors fail as reasoning assistants with two complementary gaps: a language-side gap, where editors trained as passive instruction-followers cannot map an abstract question to an appropriate visual transformation, and a generation-side gap, where edit correctness degrades as reasoning depth grows. Guided by this analysis, we introduce ETCHR (Editing To Clarify and Harness Reasoning), a question-conditioned, reasoning-aware image editor decoupled from the downstream understanding model and trained with a two-stage recipe targeted at the two gaps: Reasoning Imitation via supervised fine-tuning on edit trajectories, followed by Reasoning Enhancement with VLM-derived rewards for edit correctness and downstream reasoning accuracy. Since the editor is decoupled, ETCHR plugs into different open- and closed-source MLLMs in a training-free manner. Across five task families (fine-grained perception, chart understanding, logic reasoning, jigsaw restoration, and 3D understanding), ETCHR raises average Pass@1 from 55.95 to 60.77 (+4.82) with Qwen3-VL-8B, from 65.08 to 70.55 (+5.47) with Gemini-3.1-Flash-Lite, and from 76.55 to 81.16 (+4.61) with the 1T-parameter MoE model Kimi K2.5.