Multi-agent AI automates excited-state molecular simulations workflows
PULSES: multi-agent AI for autonomous excited-state model building and dynamics
Multiagent Systems
Summary
Simulating how molecules behave when they absorb light needs complex and slow calculations. The authors created PULSES, a multi-agent AI system that automates these calculations while staying within expert-defined scientific rules. It helps build and test machine-learned models for different molecules automatically, speeding up the process without assuming the results are correct unless validated. They tested PULSES on various molecules and showed it can handle complex chemical simulations with human oversight.
What this means in practice
- •For computational chemists: Automatically build and deploy validated excited-state models across diverse molecules within expert-set scientific boundaries.
- •For materials simulation teams: Accelerate photochemical and excited-state dynamic simulations by coordinating AI-driven workflows with human oversight to ensure scientific rigor.
Authors
Fangning Ren, Lechen Dong, Xu Chen, Weilin Zou, Bushra Alam, Fang Liu
Abstract
Simulating molecular excited-state processes requires resolving electronic and nuclear dynamics, but the cost of direct quantum-chemical calculations limits accessible system sizes and timescales. Machine-learning models can extend these simulations, yet they often need to be tailored to specific molecular systems and scientific objectives. Building and deploying such models requires coordinated decisions across conformational sampling, quantum-chemical labelling, model training, validation and dynamics. Here we introduce Paired agents for Unified Learning and Simulation of Excited States (PULSES), a multi-agent system that automates this workflow within expert-approved boundaries. A human expert and planner define the scientific objective, methods and decision boundaries, while an orchestrator coordinates domain agents and artifact-specific scientific assurance during execution. We evaluate PULSES on 15 computational chemistry tasks and demonstrate end-to-end applications to perylene exciton Hamiltonians, solvent-dependent biphenyl relaxation, and excited-state proton transfer in 10-hydroxybenzo[h]quinoline. These results demonstrate traceable, expert-bounded construction and deployment of specialized excited-state models, while retaining scientific validation as a requirement rather than assuming that successful execution establishes correctness.