cs.CVJun 11, 2025

LLM-to-Phy3D: Physically Conform Online 3D Object Generation with LLMs

Authors: Melvin Wong, Yueming Lyu, Thiago Rios, Stefan Menzel, Yew-Soon Ong

Organizations: College of Computing & Data Science, Nanyang Technological University, Singapore · Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore · Honda Research Institute Europe (HRI-EU), Offenbach am Main, Germany

Abstract

The emergence of generative artificial intelligence (GenAI) and large language models (LLMs) has revolutionized the landscape of digital content creation in different modalities. However, its potential use in Physical AI for engineering design, where the production of physically viable artifacts is paramount, remains vastly underexplored. The absence of physical knowledge in existing LLM-to-3D models often results in outputs detached from real-world physical constraints. To address this gap, we introduce LLM-to-Phy3D, a physically conform online 3D object generation that enables existing LLM-to-3D models to produce physically conforming 3D objects on the fly. LLM-to-Phy3D introduces a novel online black-box refinement loop that empowers large language models (LLMs) through synergistic visual and physics-based evaluations. By delivering directional feedback in an iterative refinement process, LLM-to-Phy3D actively drives the discovery of prompts that yield 3D artifacts with enhanced physical performance and greater geometric novelty relative to reference objects, marking a substantial contribution to AI-driven generative design. Systematic evaluations of LLM-to-Phy3D, supported by ablation studies in vehicle design optimization, reveal various LLM improvements gained by 4.5% to 106.7% in producing physically conform target domain 3D designs over conventional LLM-to-3D models. The encouraging results suggest the potential general use of LLM-to-Phy3D in Physical AI for scientific and engineering applications.

Figures & tables

Appendix figures & tables15 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. PhyMAGIC: Physical Motion-Aware Generative Inference with Confidence-guided LLM

    May 22, 2025Siwei Meng, Yawei Luo, Ping LiuPhysics-Informed Generative ModelingPhysical Consistency in Video Generation

  2. Physics-in-the-Loop: A Hybrid Agentic Architecture for Validated CAD Engineering Design

    May 19, 2026Elias Berger, Muhammad Usama, Jan Mehlstäubl +2Text-to-CAD Generation

  3. SurfScaff3D: Bridging Geometric and Semantic Representations for LLM-based 3D Object Generation

    Nov 8, 2026Anay Loya, Rishi Gupta, Arnav Samal +1Text-to-3D GenerationPart-Level 3D Generation