Bridging Visual Intuition and Chemical Expertise: An Autonomous Analysis Framework for Nonadiabatic Dynamics Simulations via Mentor-Engineer-Student Collaboration

TL;DR

VisU is a vision-driven AI framework that automates the analysis of nonadiabatic molecular dynamics, combining visual reasoning and chemical expertise to identify reaction pathways and motions, reducing manual effort.

Contribution

This work introduces VisU, a novel collaborative AI system that integrates large language models for autonomous analysis of excited-state dynamics simulations.

Findings

Successfully identifies reaction channels and nuclear motions

Generates professional academic reports automatically

Reduces manual interpretation in nonadiabatic dynamics analysis

Abstract

Analyzing nonadiabatic molecular dynamics trajectories traditionally heavily relies on expert intuition and visual pattern recognition, a process that is difficult to formalize. We present VisU, a vision-driven framework that leverages the complementary strengths of two state-of-the-art large language models to establish a "virtual research collective." This collective operates through a "Mentor-Engineer-Student" paradigm that mimics the collaborative intelligence of a professional chemistry laboratory. Within this ecosystem, the Mentor provides physical intuition through visual reasoning, while the Engineer adaptively constructs analysis scripts, and the Student executes the pipeline and manages the data and results. VisU autonomously orchestrates a four-stage workflow comprising Preprocessing, Recursive Channel Discovery, Important-Motion Identification, and Validation/Summary. This systematic approach identifies reaction channels and key nuclear motions while generating professional academic reports. By bridging visual insight with chemical expertise, VisU establishes a new paradigm for human-AI collaboration in the analysis of excited-state dynamics simulation results, significantly reducing dependence on manual interpretation and enabling more intuitive, scalable mechanistic discovery.