AI4S-SDS: A Neuro-Symbolic Solvent Design System via Sparse MCTS and Differentiable Physics Alignment

Researchers introduced AI4S-SDS, a neuro-symbolic framework combining multi-agent collaboration with Monte Carlo Tree Search for automated chemical formulation design. The system addresses LLM limitations in materials science applications and successfully identified a novel photoresist developer formulation that matches commercial benchmarks in preliminary lithography experiments.

• →AI4S-SDS combines neuro-symbolic AI with Monte Carlo Tree Search to navigate high-dimensional chemical design spaces more effectively than existing LLM agents.
• →The framework introduces Sparse State Storage with Dynamic Path Reconstruction to overcome context window limitations in long-horizon reasoning.
• →A Global-Local Search Strategy with memory-driven planning and Sibling-Aware Expansion improves exploration diversity and reduces local convergence.
• →The system integrates a Differentiable Physics Engine to ensure physical feasibility under thermodynamic constraints.
• →Preliminary experiments demonstrated the discovery of a competitive photoresist developer formulation for lithography applications.