arXiv cs.MA· Fangning Ren, Lechen Dong, Xu Chen, Weilin Zou, Bushra Alam, Fang Liu·· 12 小时前AI 评分31
PULSES：用于自主构建激发态模型与动力学模拟的多智能体 AI 系统
PULSES: multi-agent AI for autonomous excited-state model building and dynamics
AI 导读
PULSES 是一个多智能体系统，可在专家设定的边界内自动完成激发态机器学习模型从构象采样、量子化学标注、训练、验证到动力学模拟的全流程。研究在 15 项计算化学任务上评估了该系统，并端到端应用于苝激子哈密顿量、溶剂依赖的联苯弛豫以及 10-羟基苯并[h]喹啉的激发态质子转移。
正文 · 原文
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.
| Subjects: | Chemical Physics (physics.chem-ph); Multiagent Systems (cs.MA) |
| Cite as: | arXiv:2610.32392 [physics.chem-ph] |
| (or arXiv:2610.32392v1 [physics.chem-ph] for this version) | |
| https://doi.org/10.48550/arXiv.2610.32392 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Fang Liu [view email]
[v1]
Fri, 23 Oct 2026 09:17:05 UTC (7,370 KB)
来源：arXiv cs.MA · arxiv.org