PULSES: multi-agent AI for autonomous excited-state model building and dynamics
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.
Related
- Toward Autonomous Extraction and Building of Machine-Readable Molecular Models from Publications Using Large Language Models
- Active-Space Selection in Nonadiabatic Dynamics Simulations of Dense Manifolds of Excited States: When Local Diabatization Needs Great Care
- Anisotropic exciton diffusion in O-IDTBR from first-principles molecular dynamics in the first excited state
- Excited-state dynamics and photo-reaction pathways of 4-nitrothiophenol in solution investigated by time-resolved soft X-ray absorption spectroscopy
- Short-term thermal stratification induces hypoxia-related nutrient pulses which reshapes cyanobacterial dynamics in a shallow lake
BibTeX
@misc{ren2026pulses,
title = {{PULSES: multi-agent AI for autonomous excited-state model building and dynamics}},
author = {Fangning Ren and Lechen Dong and Xu Chen and Weilin Zou and Bushra Alam and Fang Liu},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.32392},
eprint = {2610.32392},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.32392},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - UNPB
TI - PULSES: multi-agent AI for autonomous excited-state model building and dynamics
AU - Fangning Ren
AU - Lechen Dong
AU - Xu Chen
AU - Weilin Zou
AU - Bushra Alam
AU - Fang Liu
PY - 2026
DA - 2026/10/23
PB - arXiv
DO - 10.48550/arxiv.2610.32392
UR - https://arxiv.org/abs/2610.32392
AB - 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.
ER -