Enhanced Conditional Generation of Double Perovskite by Knowledge-Guided Language Model Feedback

TL;DR

This paper presents a multi-agent, knowledge-guided language model framework for designing double perovskites, significantly improving the validity and stability of generated compositions without additional training data.

Contribution

It introduces a novel multi-agent framework that integrates domain knowledge and text gradients to enhance conditional material generation, surpassing previous methods in validity and stability.

Findings

Achieved over 98% compositional validity in generated DPs.

Up to 54% of candidates were stable or metastable.

Knowledge-guided gradients outperform pure LLM generation and prior GAN-based methods.

Abstract

Double perovskites (DPs) are promising candidates for sustainable energy technologies due to their compositional tunability and compatibility with low-energy fabrication, yet their vast design space poses a major challenge for conditional materials discovery. This work introduces a multi-agent, text gradient-driven framework that performs DP composition generation under natural-language conditions by integrating three complementary feedback sources: LLM-based self-evaluation, DP-specific domain knowledge-informed feedback, and ML surrogate-based feedback. Analogous to how knowledge-informed machine learning improves the reliability of conventional data-driven models, our framework incorporates domain-informed text gradients to guide the generative process toward physically meaningful regions of the DP composition space. Systematic comparison of three incremental configurations, (i) pure LLM generation, (ii) LLM generation with LLM reasoning-based feedback, and (iii) LLM generation with domain knowledge-guided feedback, shows that iterative guidance from knowledge-informed gradients improves stability-condition satisfaction without additional training data, achieving over 98% compositional validity and up to 54% stable or metastable candidates, surpassing both the LLM-only baseline (43%) and prior GAN-based results (27%). Analyses of ML-based gradients further reveal that they enhance performance in in-distribution (ID) regions but become unreliable in out-of-distribution (OOD) regimes. Overall, this work provides the first systematic analysis of multi-agent, knowledge-guided text gradients for DP discovery and establishes a generalizable blueprint for MAS-driven generative materials design aimed at advancing sustainable technologies.