SOURCE-LINKED INTELLIGENCE

CoMPASS: Collaborative Molecular Property Prediction via Adaptive Small-Large Model Synergy

arXiv · AI, language, vision and robotics · article · Aug 31, 2026 · UTC

Accurate molecular property prediction requires both statistical reliability and chemical reasoning. Graph neural networks can be calibrated directly on labeled assays but remain limited by the coverage of their training data. Large language models (LLMs) can compare molecular evidence and articulate chemical rationales, yet are unreliable as standalone quantitative predictors. The central challenge is therefore to determine when an LLM should influence a calibrated model and by how much. Here we present CoMPASS, a retrieval-calibrated framework for small-large model collaboration. CoMPASS ret

Read original source ↗ Open in workspace

recordType

paper

region

Global