# LLM-Craft: Robotic Crafting of Elasto-Plastic Objects with Large Language Models

arXiv: https://arxiv.org/abs/2406.08648 · HTML: https://mlsanity.com/paper/2406.08648/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Jun 2024.

## Built on by (most cited first, 7 of 7)

- [LLM-3D Print: Large Language Models To Monitor and Control 3D Printing](https://mlsanity.com/paper/2408.14307/) (2024)
- [Explain Like I'm Five: Using LLMs to Improve PDE Surrogate Models with Text](https://mlsanity.com/paper/2410.01137/) (2024)
- [Agentic Additive Manufacturing Alloy Evaluation](https://mlsanity.com/paper/2510.02567/) (2025)
- [Understanding Physical Properties of Unseen Deformable Objects by Leveraging Large Language Models and Robot Actions](https://mlsanity.com/paper/2506.03760/) (2025)
- [PinchBot: Long-Horizon Deformable Manipulation with Guided Diffusion Policy](https://mlsanity.com/paper/2507.17846/) (2025)
- [In-situ process monitoring for defect detection in wire-arc additive manufacturing: an agentic AI approach](https://mlsanity.com/paper/2604.09889/) (2026)
- [Visual Sculpting: Visually-Aligned Planning Representations for Long-Horizon Robot Clay Sculpting](https://mlsanity.com/paper/2605.17556/) (2026)

## Abstract (arXiv)

When humans create sculptures, we are able to reason about how geometrically we need to alter the clay state to reach our target goal. We are not computing point-wise similarity metrics, or reasoning about low-level positioning of our tools, but instead determining the higher-level changes that need to be made. In this work, we propose LLM-Craft, a novel pipeline that leverages large language models (LLMs) to iteratively reason about and generate deformation-based crafting action sequences. We simplify and couple the state and action representations to further encourage shape-based reasoning. To the best of our knowledge, LLM-Craft is the first system successfully leveraging LLMs for complex deformable object interactions. Through our experiments, we demonstrate that with the LLM-Craft framework, LLMs are able to successfully create a set of simple letter shapes. We explore a variety of rollout strategies, and compare performances of LLM-Craft variants with and without an explicit goal shape images. For videos and prompting details, please visit our project website: https://sites.google.com/andrew.cmu.edu/llmcraft/home