# ViSculpt: Visual-Centric Agentic Geometry Editing

arXiv: https://arxiv.org/abs/2608.24169 · HTML: https://mlsanity.com/paper/2608.24169/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use.
- Builds on 28 of its 57 references that are in the map.
- First posted on arXiv 25 Aug 2026.

## Placed in

- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 28 of 28)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Prompt-to-Prompt Image Editing with Cross Attention Control](https://mlsanity.com/paper/2208.01626/) (2022)
- [SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities](https://mlsanity.com/paper/2401.12168/) (2024)
- [CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assets](https://mlsanity.com/paper/2406.13897/) (2024)
- [CLIP-Mesh: Generating textured meshes from text using pretrained image-text models](https://mlsanity.com/paper/2203.13333/) (2022)
- [Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer](https://mlsanity.com/paper/2511.22699/) (2025)
- [DeepCAD: A Deep Generative Network for Computer-Aided Design Models](https://mlsanity.com/paper/2105.09492/) (2021)
- [Native and Compact Structured Latents for 3D Generation](https://mlsanity.com/paper/2512.14692/) (2025)
- [Hunyuan3D 2.1: From Images to High-Fidelity 3D Assets with Production-Ready PBR Material](https://mlsanity.com/paper/2506.15442/) (2025)
- [SAM3D: Segment Anything in 3D Scenes](https://mlsanity.com/paper/2306.03908/) (2023)
- [Infinite Photorealistic Worlds using Procedural Generation](https://mlsanity.com/paper/2306.09310/) (2023)
- [Infinigen Indoors: Photorealistic Indoor Scenes using Procedural Generation](https://mlsanity.com/paper/2406.11824/) (2024)
- [CSGNet: Neural Shape Parser for Constructive Solid Geometry](https://mlsanity.com/paper/1712.08290/) (2017)
- [Anything-3D: Towards Single-view Anything Reconstruction in the Wild](https://mlsanity.com/paper/2304.10261/) (2023)
- [UCSG-Net -- Unsupervised Discovering of Constructive Solid Geometry Tree](https://mlsanity.com/paper/2006.09102/) (2020)
- [Scenethesis: A Language and Vision Agentic Framework for 3D Scene Generation](https://mlsanity.com/paper/2505.02836/) (2025)
- [GPT4Motion: Scripting Physical Motions in Text-to-Video Generation via Blender-Oriented GPT Planning](https://mlsanity.com/paper/2311.12631/) (2023)
- [OmniPart: Part-Aware 3D Generation with Semantic Decoupling and Structural Cohesion](https://mlsanity.com/paper/2507.06165/) (2025)
- [Instant3dit: Multiview Inpainting for Fast Editing of 3D Objects](https://mlsanity.com/paper/2412.00518/) (2024)
- [Img2CAD: Conditioned 3D CAD Model Generation from Single Image with Structured Visual Geometry](https://mlsanity.com/paper/2410.03417/) (2024)
- [BlenderLLM: Training Large Language Models for Computer-Aided Design with Self-improvement](https://mlsanity.com/paper/2412.14203/) (2024)
- [L3GO: Language Agents with Chain-of-3D-Thoughts for Generating Unconventional Objects](https://mlsanity.com/paper/2402.09052/) (2024)
- [3D-PreMise: Can Large Language Models Generate 3D Shapes with Sharp Features and Parametric Control?](https://mlsanity.com/paper/2401.06437/) (2024)
- [Agents of Change: Self-Evolving LLM Agents for Strategic Planning](https://mlsanity.com/paper/2506.04651/) (2025)
- [3D Mesh Editing using Masked LRMs](https://mlsanity.com/paper/2412.08641/) (2024)
- [Agentic 3D Scene Generation with Spatially Contextualized VLMs](https://mlsanity.com/paper/2505.20129/) (2025)

## Built on by (most cited first, 1 of 1)

- [AutoGUIWorld: Image Generators as Visual World Models for GUI Agent](https://mlsanity.com/paper/2610.01215/) (2026)

## Abstract (arXiv)

3D geometry editing is a critical yet labor-intensive part of the graphics pipeline, requiring artists to translate creative intent into precise operations in complex professional software. Large language models (LLMs) have shown promise for script-based 3D creation, but script generation is less suited to perception-driven editing of arbitrary existing meshes, where execution must remain visually grounded and untouched regions should be preserved. We present a visual-centric, training-free multi-agent system that edits existing 3D meshes directly in Blender by emulating the iterative workflow of human artists. Rather than generating scripts or regenerating geometry, our system operates through the Blender GUI: multimodal LLM agents observe the viewport, reason about the current mesh state, and execute localized edits through simulated user interactions. Experiments on a curated benchmark provide initial evidence that this agentic approach can follow natural language instructions, perform representative localized mesh edits, and preserve the overall identity of the input asset. Our results highlight a complementary regime for language-driven 3D editing: direct in-place modification of existing meshes within the native 3D editing workflow. We view this work as an exploratory step toward visual-centric agentic geometry editing in professional graphics software.