EditHero: A Benchmark for Long-Horizon Part-Level 3D Editing and Vibe Modeling

Hugging Face Daily Papers Papers
3d-editing benchmark llm-agents multimodal long-horizon mesh-editing

Summary

EditHero is the first benchmark for long-horizon, part-level 3D editing with natural-language instructions and target images, comparing non-agentic regeneration methods against LLM/VLM agents that edit meshes via code. Non-agentic methods often miss requested changes and disturb fixed regions, while LLM agents follow instructions better and preserve unedited parts, at the cost of slower edits.

3D editing methods are usually tested on a single edit, yet an asset is built through a long sequence of revisions, each of which must implement the requested change while leaving everything else unchanged. We introduce EditHero, to our knowledge the first benchmark for long-horizon, part-level 3D editing, with natural-language instructions and target images for both geometry and texture. A deterministic assembly engine produces the exact target after every edit, and every sequence is reviewed by hand. We use EditHero to compare 2 opposite approaches to 3D editing. Non-agentic methods operate top down, regenerating the object from a learned 3D representation and inferring what to keep. In contrast, LLM/VLM agents operate bottom up, editing through code that inspects the mesh and rewrites only the parts required by instructions. The non-agentic methods often miss the requested change and disturb regions that should stay fixed. Most LLMs follow instructions more closely, and all of them preserve the unedited parts better, but each of their edits takes minutes. We will release the engine and the edit sequences to support research on reliable iterative 3D editing.
Original Article
View Cached Full Text

Cached at: 10/05/26, 04:46 AM

Paper page - EditHero: A Benchmark for Long-Horizon Part-Level 3D Editing and Vibe Modeling

Source: https://huggingface.co/papers/2610.02298 Authors:

,

,

,

,

,

,

,

,

,

,

Abstract

3Deditingmethodsareusuallytestedonasingleedit,yetanassetisbuiltthroughalongsequenceofrevisions,eachofwhichmustimplementtherequestedchangewhileleavingeverythingelseunchanged.WeintroduceEditHero,toourknowledgethefirstbenchmarkforlong-horizon,part-level3Dediting,withnatural-languageinstructionsandtargetimagesforbothgeometryandtexture.Adeterministicassemblyengineproducestheexacttargetaftereveryedit,andeverysequenceisreviewedbyhand.WeuseEditHerotocompare2oppositeapproachesto3Dediting.Non-agenticmethodsoperatetopdown,regeneratingtheobjectfromalearned3Drepresentationandinferringwhattokeep.Incontrast,LLM/VLMagentsoperatebottomup,editingthroughcodethatinspectsthemeshandrewritesonlythepartsrequiredbyinstructions.Thenon-agenticmethodsoftenmisstherequestedchangeanddisturbregionsthatshouldstayfixed.MostLLMsfollowinstructionsmoreclosely,andallofthempreservetheuneditedpartsbetter,buteachoftheireditstakesminutes.Wewillreleasetheengineandtheeditsequencestosupportresearchonreliableiterative3Dediting.

View arXiv pageView PDFProject pageGitHub1Add to collection

Get this paper in your agent:

hf papers read 2610\.02298

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2610.02298 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2610.02298 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2610.02298 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

VEFX-Bench: A Holistic Benchmark for Generic Video Editing and Visual Effects

Hugging Face Daily Papers

VEFX-Bench introduces a large-scale human-annotated video editing dataset (5,049 examples) with multi-dimensional quality labels and a specialized reward model for standardized evaluation of video editing systems. The paper addresses the lack of comprehensive benchmarks in AI-assisted video creation by providing VEFX-Dataset, VEFX-Reward, and a 300-video-prompt benchmark that reveals gaps in current editing models.