ML4Molecules: Agentic Systems for Molecular Sciences
From in-silico chemists and closed-loop labs to failures at counting carbons.
Agentic large language model systems are moving from conversational and coding assistants to co-scientists in the molecular sciences, such as planning syntheses, calling domain tools, and closing experimental loops with laboratory automation. Recent demonstrations span autonomous drug repurposing, retrosynthesis, and genome-wide virtual screening, all built on stacks of learned representations, predictors, and simulators. Yet careful benchmarking has exposed striking failures at seemingly simple tasks: tool-augmented agents reach only around 50% accuracy on chemical cost estimation, chemistry language models fail systematic symbolic reasoning on molecular graphs, and single-cell foundation models for perturbation prediction do not outperform linear baselines. This workshop takes the contrast between agentic ambition and methodological fragility as its starting point with explicit space for negative results, rigorous baselines, and benchmark contributions alongside methodological advances.
Invited Speakers
Andrew White
FutureHouseCo-founder and head of science at FutureHouse; pioneer of agentic AI systems for science (ChemCrow, ether0, PaperQA).
Francesca Grisoni
TU EindhovenAssociate Professor leading the Molecular Machine Learning team, bridging AI and the wet-lab for drug discovery.
Yanyan Lan
Tsinghua UniversityDeputy Dean and professor at the Institute for AI Industry Research (AIR); machine learning, information retrieval, and AI for Science.
Gábor Csányi
University of Cambridge & Max Planck Institute for Polymer ResearchPioneer of machine-learning interatomic potentials and first-principles property prediction.
Jean-Philippe Vert
BioptimusCo-founder and CEO of Bioptimus, building foundation models for biology and medicine; member of the French National Academy of Technologies.
Philippe Schwaller
EPFLAssistant Professor leading the Laboratory of Artificial Chemical Intelligence; AI-accelerated synthesis and chemical reasoning.
Panelists
Organizers
Program Committee Chairs
Supporters
The workshop proposal is supported by the ELLIS unit Linz and the ELLIS unit Cambridge.
Sponsors
Contact us at ml4molecules@ml.jku.at to support this workshop.
Contact
For questions about the workshop, contact us at ml4molecules@ml.jku.at.