MatEvolve: A Synergistic Symbolic–LLM Agent for Multi-Objective Materials Design

Qianyou Zhong, Dingyang Lv, Bowen Fang, Baole Wei, Xiangran Cheng, Hongwei Du, Feng Yu

Keywords: Evolutionary Agents, AI for Science, Materials Design

TL;DR: MatEvolve reframes materials design as closed-loop insight–exploration–validation via a symbolic–LLM agent with MEL, dynamic knowledge injection, and two-stage exploration, achieving >30% gains over enumeration–screening.

Abstract: The design of novel materials is fundamentally constrained by the immense chemical space, which renders traditional enumeration-screening methodology computationally prohibitive and inefficient. This paper introduces a paradigm shift towards insight-exploration-validation, enabling an intelligent and evolutionary exploration of material design pathways. We actualize this paradigm through MatEvolve, a synergistic symbolic–LLM agent that reconceptualizes material design as a closed-loop, programmatic evolution task. Central to MatEvolve is a novel symbolic formalism, Material Edit Language, which empowers the agent to programmatically take chemical operations. The exploration trajectory is directed by a multifaceted guidance strategy, comprising a dynamic knowledge injection mechanism and a two-stage exploration strategy that balances broad exploration and deep optimization. Furthermore, a multi-objective fitness landscape ensures directional and efficient navigational guidance. These integrated strategies contribute to a 32.2% improvement over direct material structure modification. Crucially, comparisons demonstrate that our insight-exploration-validation paradigm outperforms the traditional enumeration-screening approach by 33.6%, highlighting its superior efficacy in navigating vast design spaces.

Primary Area: applications to physical sciences (physics, chemistry, biology, etc.)

Submission Number: 23535