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

• URL: http://arxiv.org/abs/2604.27300v1
• Date: Thu, 30 Apr 2026 01:22:15 GMT
• Title: METASYMBO: Multi-Agent Language-Guided Metamaterial Discovery via Symbolic Latent Evolution
• Abstract summary: MetaSymbO is a framework for language-guided Metamaterial discovery.<n>Designer interprets free-form design intents and retrieves a semantically consistent scaffold.<n> Generator synthesizes candidate microstructures in a disentangled latent space.<n>Supervisor provides fast property-aware feedback for iterative refinement.
• Score: 22.353386897563343
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• 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.

Related papers

• From Atomic to Agentic: Towards Interpretable Evaluation of LLMs' Agentic Mathematical Capabilities [103.60384544335072]
  Large Language Models (LLMs) are evolving from performing end-to-end mathematical reasoning to integrating agentic intelligence.<n>Our framework aligns problem-solving agentic behaviors with a structured taxonomy of reusable mathematical atomic capabilities.<n> Experiments reveal that models with similar end-to-end accuracy can exhibit markedly different agentic capability profiles.
  arXiv  Detail & Related papers  (2026-08-27T10:52:06Z)
• A Systematic Survey and Benchmark of Deep Learning for Molecular Property Prediction in the Foundation Model Era [57.5440098776759]
  Molecular property prediction integrates quantum chemistry, cheminformatics, and deep learning to connect molecular structure with biological behavior.<n>This survey traces four complementary paradigms, including Quantum, Descriptor Machine Learning, Geometric Deep Learning, and Foundation Models.<n> Benchmark analyses integrate evidence from both widely used datasets and datasets reflecting industry perspectives.
  arXiv  Detail & Related papers  (2026-04-17T15:16:33Z)
• OMNIFLOW: A Physics-Grounded Multimodal Agent for Generalized Scientific Reasoning [51.33849811496781]
  Large Language Models (LLMs) have demonstrated exceptional logical reasoning capabilities but frequently struggle with the continuous dynamics by Partial Differential Equations (PDEs)<n>We propose OMNIFLOW, a multimodal-symbolic architecture designed to ground frozen LLMs in fundamental physical laws without requiring domain-specific parameter updates.<n>We evaluate it on a benchmark spanning microscopic turbulence, theoretical Navier-Stokes, and macroscopic global weather forecasting.
  arXiv  Detail & Related papers  (2026-03-16T18:29:01Z)
• Towards Agentic Intelligence for Materials Science [73.4576385477731]
  This survey advances a unique pipeline-centric view that spans from corpus curation and pretraining to goal-conditioned agents interfacing with simulation and experimental platforms.<n>To bridge communities and establish a shared frame of reference, we first present an integrated lens that aligns terminology, evaluation, and workflow stages across AI and materials science.
  arXiv  Detail & Related papers  (2026-01-29T23:48:43Z)
• Meta-GPT: Decoding the Metasurface Genome with Generative Artificial Intelligence [0.4964239559434301]
  We introduce METASTRINGS, a symbolic language for photonics that expresses nanostructures as textual sequences.<n>We build a foundation transformer model trained on METASTRINGS and finetuned with physics-informed supervised, reinforcement, and chain-of-thought learning.<n>Results demonstrate that Meta-GPT can learn the compositional rules of light-matter interactions through METASTRINGS.
  arXiv  Detail & Related papers  (2025-12-15T00:09:14Z)
• Lost in Tokenization: Context as the Key to Unlocking Biomolecular Understanding in Scientific LLMs [78.18336140706471]
  Sci-LLMs have emerged as a promising frontier for accelerating biological discovery.<n>Current strategies limit Sci-LLMs' reasoning capacity when processing raw biomolecular sequences.<n>We show that a more effective strategy is to provide Sci-LLMs with high-level structured context.
  arXiv  Detail & Related papers  (2025-10-27T09:03:21Z)
• MetaBench: A Multi-task Benchmark for Assessing LLMs in Metabolomics [23.71774159970153]
  Large Language Models (LLMs) have demonstrated remarkable capabilities on general text.<n> Metabolomics presents unique challenges with its complex biochemical pathways, heterogeneous identifier systems, and fragmented databases.<n>We introduce MetaBench, the first benchmark for metabolomics assessment.
  arXiv  Detail & Related papers  (2025-10-16T17:55:14Z)
• MetamatBench: Integrating Heterogeneous Data, Computational Tools, and Visual Interface for Metamaterial Discovery [35.74367505796871]
  We introduce a unified framework, named MetamatBench, that operates on three levels.<n>At the data level, we integrate and standardize 5 heterogeneous, multi-modal metamaterial datasets.<n>The ML level provides a comprehensive toolkit that adapts 17 state-of-the-art ML methods for metamaterial discovery.<n>The user level features a visual-interactive interface that bridges the gap between complex ML techniques and non-ML researchers.
  arXiv  Detail & Related papers  (2025-05-08T19:23:59Z)
• MetaScientist: A Human-AI Synergistic Framework for Automated Mechanical Metamaterial Design [39.56799107018762]
  We present MetaScientist, a human-in-the-loop system that integrates advanced AI capabilities with expert oversight.<n>At each phase, domain experts iteratively validate the system outputs, and provide feedback and supplementary materials to ensure the alignment of the outputs with scientific principles and human preferences.
  arXiv  Detail & Related papers  (2024-12-20T15:20:57Z)
• Reflection-Bench: Evaluating Epistemic Agency in Large Language Models [10.801745760525838]
  Epistemic agency is the ability to flexibly construct, adapt, and monitor beliefs about dynamic environments.<n>We propose Reflection-Bench, a benchmark consisting of seven tasks with long-term relevance and minimization of data leakage.<n>Our findings suggest several promising research directions, including enhancing core cognitive functions, improving cross-functional coordination, and developing adaptive processing mechanisms.
  arXiv  Detail & Related papers  (2024-10-21T17:59:50Z)
• X2-DFD: A framework for eXplainable and eXtendable Deepfake Detection [55.77552681618732]
  X2-DFD is an eXplainable and eXtendable framework based on multimodal large-language models (MLLMs) for deepfake detection.<n>The first stage, Model Feature Assessment, systematically evaluates the detectability of forgery-related features for the MLLM.<n>The second stage, Explainable dataset Construction, consists of two key modules: Strong Feature Strengthening and Weak Feature Supplementing.<n>The third stage, Fine-tuning and Inference, involves fine-tuning the MLLM on the constructed dataset and deploying it for final detection and explanation.
  arXiv  Detail & Related papers  (2024-10-08T15:28:33Z)
• Geometric Deep Learning for Structure-Based Drug Design: A Survey [83.87489798671155]
  Structure-based drug design (SBDD) leverages the three-dimensional geometry of proteins to identify potential drug candidates. Recent advancements in geometric deep learning, which effectively integrate and process 3D geometric data, have significantly propelled the field forward.
  arXiv  Detail & Related papers  (2023-06-20T14:21:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.