EvoMD-LLM: Learning the Language of Species Evolution in Reactive Molecular Dynamics

2026-05-28

AI Summary

This work addresses the challenge that large language models struggle to effectively capture the temporal structure of species evolution in reactive molecular dynamics. To overcome this limitation, the authors transform molecular trajectories into symbolic time series and introduce a “temporal scaffolding” mechanism, which explicitly encodes chemical species and their residence durations as discrete language tokens. This design endows the autoregressive language model with a structured inductive bias, substantially reducing invalid or hallucinated outputs and enhancing interpretability. Evaluated on multiple temporal prediction tasks, the proposed approach achieves up to 66.14% accuracy—outperforming both conventional sequence models and language model baselines—and generates chemically plausible explanations for its predictions.

Abstract

While large language models (LLMs) excel at static scientific reasoning, they struggle to model the temporal structure of dynamic physical processes. We present EvoMD-LLM (Evolutionary Molecular Dynamics Large Language Model), a framework that reformulates species-level molecular dynamics as a symbolic temporal language modeling problem. Reactive MD trajectories are discretized into sequences of molecular events, where each token represents a chemical species augmented with its persistence duration, enabling standard autoregressive LLMs to learn compositional evolution over time through efficient fine-tuning. A key component of EvoMD-LLM is temporal scaffolding, which treats event duration as an explicit linguistic token and serves as a structured inductive bias, significantly reducing invalid or hallucinated molecular outputs compared to conventional sequence modeling approaches. We evaluate EvoMD-LLM on multiple temporal prediction tasks, achieving up to 66.14% accuracy and consistently outperforming sequential neural networks and language-based baselines. Beyond quantitative improvements, we qualitatively observe that the model is capable of generating interpretations for its own predictions by incorporating relevant chemical knowledge, even though it was not explicitly supervised with paired trajectory-explanation data. These results demonstrate that symbolic temporal language modeling provides an effective framework for grounding LLMs in dynamic physical simulations.

Problem

• large language models
• molecular dynamics
• temporal modeling
• species evolution
• reactive simulations

Innovation

• symbolic temporal language modeling
• temporal scaffolding
• reactive molecular dynamics
• large language models
• molecular event sequences