Polymer-Agent: Large Language Model Agent for Polymer Design
This addresses the problem of resource-intensive trial-and-error in polymer design for laboratory researchers, though it appears incremental as it builds on existing machine learning methods for property prediction and latent space search.
The authors tackled the challenge of on-demand polymer discovery by developing a closed-loop polymer structure-property predictor integrated into a terminal, powered by LLM reasoning to provide property prediction, property-guided polymer structure generation, and structure modification capabilities, with results including guidance by synthetic accessibility and complexity scores to ensure synthetically accessible structures.
On-demand Polymer discovery is essential for various industries, ranging from biomedical to reinforcement materials. Experiments with polymers have a long trial-and-error process, leading to use of extensive resources. For these processes, machine learning has accelerated scientific discovery at the property prediction and latent space search fronts. However, laboratory researchers cannot readily access codes and these models to extract individual structures and properties due to infrastructure limitations. We present a closed-loop polymer structure-property predictor integrated in a terminal for early-stage polymer discovery. The framework is powered by LLM reasoning to provide users with property prediction, property-guided polymer structure generation, and structure modification capabilities. The SMILES sequences are guided by the synthetic accessibility score and the synthetic complexity score (SC Score) to ensure that polymer generation is as close as possible to synthetically accessible monomer-level structures. This framework addresses the challenge of generating novel polymer structures for laboratory researchers, thereby providing computational insights into polymer research.