MSP-LLM: A Unified Large Language Model Framework for Complete Material Synthesis Planning

TL;DR

MSP-LLM introduces a comprehensive LLM-based framework for material synthesis planning, integrating precursor and synthesis operation predictions into a unified, chemically consistent process to enhance AI-driven materials discovery.

Contribution

It presents the first unified LLM framework for complete MSP, combining precursor prediction and synthesis operation prediction with hierarchical and conditioning strategies.

Findings

MSP-LLM outperforms existing methods on precursor and synthesis prediction tasks.

The framework demonstrates superior performance on the complete MSP task.

MSP-LLM offers a scalable approach to accelerate materials discovery.

Abstract

Material synthesis planning (MSP) remains a fundamental and underexplored bottleneck in AI-driven materials discovery, as it requires not only identifying suitable precursor materials but also designing coherent sequences of synthesis operations to realize a target material. Although several AI-based approaches have been proposed to address isolated subtasks of MSP, a unified methodology for solving the entire MSP task has yet to be established. We propose MSP-LLM, a unified LLM-based framework that formulates MSP as a structured process composed of two constituent subproblems: precursor prediction (PP) and synthesis operation prediction (SOP). Our approach introduces a discrete material class as an intermediate decision variable that organizes both tasks into a chemically consistent decision chain. For SOP, we further incorporate hierarchical precursor types as synthesis-relevant inductive biases and employ an explicit conditioning strategy that preserves precursor-related information in the autoregressive decoding state. Extensive experiments show that MSP-LLM consistently outperforms existing methods on both PP and SOP, as well as on the complete MSP task, demonstrating an effective and scalable framework for MSP that can accelerate real-world materials discovery.