METASYMBO: Multi-Agent Language-Guided Metamaterial Discovery via Symbolic Latent Evolution

2026-04-29

AI Summary

This work addresses the challenge that existing inverse design methods for metamaterials rely on precise numerical targets and struggle to interpret ambiguous natural language intents during early-stage design. To bridge this gap, the authors propose a multi-agent framework that integrates large language models with physics-aware generative mechanisms, enabling semantic-guided innovative design through symbol-driven latent space evolution. The approach employs a tri-agent architecture—comprising Designer, Generator, and Supervisor agents—along with disentangled latent representations and programmable symbolic operators to dynamically steer the generation process during inference, balancing semantic alignment, structural novelty, and physical validity. Experiments demonstrate that the generated structures achieve 34% and 98% improvements in symmetry and periodicity, respectively, outperform baseline methods by 6–7% in language-guided scoring, and exhibit practical efficacy in designing auxetic and high-stiffness metamaterials.

Abstract

Metamaterial discovery seeks microstructured materials whose geometry induces targeted mechanical behavior. Existing inverse-design methods can efficiently generate candidates, but they typically require explicit numerical property targets and are less suitable for early-stage exploration, where researchers often begin with incomplete constraints and qualitative intents expressed in natural language. Large language models can interpret such intents, but they lack geometric awareness and physical property validity. To address this gap, we propose MetaSymbO, a multi-agent framework for language-guided Metamaterial discovery via Symbolic-driven latent evOlution. Specifically, MetaSymbO contains three agents: a Designer that interprets free-form design intents and retrieves a semantically consistent scaffold, a Generator that synthesizes candidate microstructures in a disentangled latent space, and a Supervisor that provides fast property-aware feedback for iterative refinement. To move beyond the limitations of reproducing known samples from literature and training data, we further introduce symbolic-driven latent evolution, which applies programmable operators over disentangled latent factors to compose, modify, and refine structures at inference time. Extensive experiments demonstrate that (i) MetaSymbO improves structural validity by up to 34% in symmetry and nearly 98% in periodicity compared to state-of-the-art baselines; (ii) MetaSymbO achieves about 6-7% higher language-guidance scores while maintaining superior structure novelty compared to advanced reasoning LLMs; (iii) qualitative analyses confirm the effectiveness of symbolic logic operators in enabling programmable semantic alignment; and (iv) realworld case studies on auxetic, high-stiffness metamaterial design further validate its practical capability.

Problem

• metamaterial discovery
• inverse design
• natural language intent
• geometric awareness
• physical property validity

Innovation

• symbolic latent evolution
• multi-agent framework
• language-guided design
• disentangled latent space
• metamaterial discovery