Reasoning-Informed Visual Editing

Hugging Face Daily Papers Papers
visual-editing benchmark reasoning multimodal large-multimodality-models agentic-framework evaluation

Summary

该论文提出了 RISEBench 及其扩展版本 RISEBench++，这是首个评估推理驱动视觉编辑（Reasoning-Informed Visual Editing）的基准，涵盖时序、因果、空间、逻辑、反事实及混合推理等六个维度，并提出训练无关的 RISE-Agent 框架，结果显示即使是 GPT-Image-2.5 Sunburst 也仅达 56.6% 准确率。

Large Multi-modality Models (LMMs) have made significant progress in visual understanding and generation, but still face challenges in visual editing, particularly in following complex instructions, preserving appearance consistency, and supporting flexible input formats. To study this gap, we introduce RISEBench, the first benchmark for evaluating Reasoning-Informed viSual Editing (RISE), and extend it to RISEBench++, a more comprehensive and fine-grained benchmark for this emerging task. RISEBench++ extends the taxonomy into a hierarchical scheme spanning six reasoning dimensions: Temporal, Causal, Spatial, Logical, and Counterfactual Reasoning, together with Hybrid Reasoning integrating multiple reasoning types across multi-turn edits. These dimensions are further decomposed into 12 subcategories and 65 fine-grained task types. We expand input formats to include multi-image conditioning and scale the benchmark to 1000 human-annotated test cases, released in English and Chinese. We also improve our evaluation framework, assessing Instruction Reasoning, Appearance Consistency, and Visual Plausibility with human judges and an LMM-as-a-judge approach for more reliable and calibrated judgements. Beyond benchmarking, we introduce RISE-Agent, a training-free agentic framework integrating reasoning-driven planning, tool-augmented execution, and verifier-guided refinement, outperforming most strong existing approaches across diverse RISE tasks. We evaluate 58 visual editing approaches, including 34 open-source models, 19 closed-source models, and 5 agentic methods. The results reveal substantial challenges in reasoning-based visual editing, with even the strongest evaluated approach, GPT-Image-2.5 Sunburst, achieving only 56.6% accuracy. RISEBench++ highlights the limitations of contemporary editing models, provides insights, and indicates future directions for reasoning-aware visual editing.
Original Article
View Cached Full Text

Cached at: 10/09/26, 06:26 AM

Paper page - Reasoning-Informed Visual Editing

Source: https://huggingface.co/papers/2610.12343 Published on Oct 8

·

Submitted byhttps://huggingface.co/zpy777

zpyon Oct 9

Authors:

,

,

,

,

,

,

,

,

,

,

,

,

,

Abstract

LargeMulti-modalityModels(LMMs)havemadesignificantprogressinvisualunderstandingandgeneration,butstillfacechallengesinvisualediting,particularlyinfollowingcomplexinstructions,preservingappearanceconsistency,andsupportingflexibleinputformats.Tostudythisgap,weintroduceRISEBench,thefirstbenchmarkforevaluatingReasoning-InformedviSualEditing(RISE),andextendittoRISEBench++,amorecomprehensiveandfine-grainedbenchmarkforthisemergingtask.RISEBench++extendsthetaxonomyintoahierarchicalschemespanningsixreasoningdimensions:Temporal,Causal,Spatial,Logical,andCounterfactualReasoning,togetherwithHybridReasoningintegratingmultiplereasoningtypesacrossmulti-turnedits.Thesedimensionsarefurtherdecomposedinto12subcategoriesand65fine-grainedtasktypes.Weexpandinputformatstoincludemulti-imageconditioningandscalethebenchmarkto1000human-annotatedtestcases,releasedinEnglishandChinese.Wealsoimproveourevaluationframework,assessingInstructionReasoning,AppearanceConsistency,andVisualPlausibilitywithhumanjudgesandanLMM-as-a-judgeapproachformorereliableandcalibratedjudgements.Beyondbenchmarking,weintroduceRISE-Agent,atraining-freeagenticframeworkintegratingreasoning-drivenplanning,tool-augmentedexecution,andverifier-guidedrefinement,outperformingmoststrongexistingapproachesacrossdiverseRISEtasks.Weevaluate58visualeditingapproaches,including34open-sourcemodels,19closed-sourcemodels,and5agenticmethods.Theresultsrevealsubstantialchallengesinreasoning-basedvisualediting,witheventhestrongestevaluatedapproach,GPT-Image-2.5Sunburst,achievingonly56.6%accuracy.RISEBench++highlightsthelimitationsofcontemporaryeditingmodels,providesinsights,andindicatesfuturedirectionsforreasoning-awarevisualediting.

View arXiv pageView PDFGitHub155Add to collection

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2610.12343 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2610.12343 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2610.12343 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

Is This Edit Correct? A Multi-Dimensional Benchmark for Reasoning-Aware Image Editing

Hugging Face Daily Papers

This paper introduces RE-Edit, a benchmark for evaluating image editing systems across five reasoning dimensions (physical, environmental, cultural, causal, referential) to assess logical consistency beyond visual plausibility. The benchmark includes 1,000 samples and evaluates ten open-source and two commercial models, showing that even advanced systems struggle with implicit multi-dimensional reasoning.

ThinkDrag: Semantic Drag-Based Image Editing with Visual Reasoning

Hugging Face Daily Papers

ThinkDrag提出了一种统一的多模态框架，将视觉推理引入基于拖拽的图像编辑，通过语义变换和显式推理轨迹解释用户意图，并发布了DragBench++基准测试，实现了最先进的编辑效果。

ETCHR: Editing To Clarify and Harness Reasoning

Hugging Face Daily Papers

ETCHR is a novel image editing approach that decouples visual reasoning from image generation, using a two-stage training process (Reasoning Imitation and Reasoning Enhancement) to improve multimodal language model performance across five visual reasoning tasks. It achieves consistent gains of 4-5% Pass@1 on models like Qwen3-VL-8B, Gemini-3.1-Flash-Lite, and Kimi K2.5.