4 papers
Agentic AI for Density-Functional Development: Revisiting r2SCAN
Santosh Adhikari, Kelsey A. Parker, Etinosa Osaro +2
We demonstrate physics-constrained agentic development of a meta-generalized gradient approximation (meta-GGA) functional using a large language model (LLM) to assist the search an…
RLEASE: Reinforcement Learning Efficient Active Space Engine
Etinosa Osaro, Abhishek Mitra, Andrew J. Jenkins +6
Selecting the active space for multireference electronic-structure calculations is a long-standing bottleneck that often requires expert chemical intuition and costly trial-and-err…
MLIPilot: LLM-Driven Auto-Research for Machine-Learned Interatomic Potentials
Etinosa Osaro, Santosh Adhikari, Stamatia Zavitsanou +2
Constructing production-quality machine-learned interatomic potentials (MLIPs) requires balancing accuracy, dynamical stability, and computational throughput under constraints that…
Using machine learning to map simulated noisy and laser-limited multidimensional spectra to molecular electronic couplings
Jonathan D. Schultz, Kelsey A. Parker, Bashir Sbaiti +1
Two-dimensional electronic spectroscopy (2DES) has enabled significant discoveries in both biological and synthetic energy-transducing systems. Although deriving chemical informati…