ETCHR：通过编辑澄清与利用推理

摘要

多模态大语言模型已推动了视觉推理的进步，然而，对于需要细粒度关注或视角变换的问题，纯文本的思维链仍是瓶颈。“以图促思”范式缩小了这一差距，但现有方法要么受限于固定的预定义工具集，要么因统一的多模态方法而产生噪声过多的中间图像。我们探索了第三种方案：使用专用的图像编辑模型，并将其与理解模型解耦。然而，现成的图像编辑器作为推理助手存在两个互补的缺陷：语言侧的缺陷——作为被动指令遵循者训练的编辑器无法将抽象问题映射到适当的视觉变换；生成侧的缺陷——随着推理深度的增加，编辑正确性会下降。基于这一分析，我们提出了ETCHR（编辑以澄清和驾驭推理），这是一种与下游理解模型解耦的、问题条件化且具有推理感知能力的图像编辑器，并通过针对这两个缺陷的两阶段配方进行训练：先通过编辑轨迹上的监督微调进行推理模仿，再通过基于VLM的奖励进行推理增强，奖励同时考虑编辑正确性和下游推理准确性。由于编辑器是解耦的，ETCHR可以即插即用，无需训练即可集成到不同的开源和闭源MLLM中。在五类任务（细粒度感知、图表理解、逻辑推理、拼图修复和3D理解）中，ETCHR将平均Pass@1指标从55.95提升至60.77（+4.82，搭配Qwen3-VL-8B），从65.08提升至70.55（+5.47，搭配Gemini-3.1-Flash-Lite），从76.55提升至81.16（+4.61，搭配1万亿参数的MoE模型Kimi K2.5）。

English

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.