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

TL;DR

VisU addresses the challenge of analyzing high-dimensional nonadiabatic dynamics trajectories by integrating vision-enabled LLMs within a Mentor-Engineer-Student collaboration to automate end-to-end analysis of NAMD data. The framework orchestrates a four-stage workflow—Preprocessing, Recursive Channel Discovery, Important-Motion Identification, and Validation/Summary—combining visual reasoning with chemical knowledge to identify reaction channels and active nuclear motions with minimal human input. In a keto isocytosine case study, VisU autonomously discovers seven candidate channels, merges mirror-symmetric channels, and reports four principal channels with quantified populations and mechanistic interpretations. The work demonstrates a scalable, human-like AI-assisted protocol for excited-state dynamics, with open-source code and data availability, offering a blueprint for AI4Chemistry workflows.

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.

Figures (4)

• Figure 1: Preprocessing pipeline implemented through the cooperation of Mentor, Engineer and Student. (a) User-provided input file (test.zip) and message. (b) Generation of the preprocessing Python script using tool calling and the provided Python function templates. (c) Final preprocess.py and the resulting XYZ files. (d) Analysis of molecular structures, including the molecular structure and atomic labels of keto isocytosine shown in mol.png. (e) Six generated descriptor sets based on RICs.
• Figure 2: "Mentor-Student" cooperation during the first iteration of unsupervised channel discovery. Based on diagnostic plots produced by the Student, the carefully prompted visual-language Mentor (Doubao-Seed-1.6-Vision) provides targeted guidance on: (a) selection of the optimal reduced-dimensional subspace, (b) choice of clustering algorithm, (c) tuning of hyperparameters, and (d) final evaluation of the resulting clusters.
• Figure 3: Identification of the dominant molecular motions, illustrated for Candidate Channel 3. (a) Two-dimensional PCA projections generated by the Student from the structural descriptors $D_{\mathrm{ring}}$, $A_{\mathrm{ring}}$, $R_{\mathrm{ring}}$, $D_{\mathrm{eg}}$, $R_{\mathrm{eg}}$, and $A_{\mathrm{eg}}$. By visually inspecting these projections, the Mentor assessed in which low-dimensional representations the initial and hopping geometries became separable. (b) Corresponding PCA component loadings, examined by the Mentor to identify the structural features most responsible for the observed channel separation. (c) Dominant molecular motions inferred by the Mentor through joint inspection of the key features and representative initial and hopping geometries.
• Figure 4: (a) Final nonadiabatic channel analysis tree. Details regarding the division and naming of different clusters can be found in the SI. (b) Averaged and (c) representative structures (hydrogen atoms omitted) for the four channels.