Scaffold-Conditioned Preference Triplets for Controllable Molecular Optimization with Large Language Models

ArXi:2604.12350v1 Announce Type: cross Molecular property optimization is central to drug discovery, yet many deep learning methods rely on black-box scoring and offer limited control over scaffold preservation, often producing unstable or biologically implausible edits. While large language models (LLMs) are promising molecular generators, optimization remains constrained by the lack of chemistry-grounded preference supervision and principled data curation. We