🎉 I’ll be at NeurIPS 2026 in Sydney presenting our work on Unlocking LLM Creativity in Science through Analogical Reasoning! If you’re interested, happy to chat about AI for scientific discovery and agents for science/medicine.

Hi, my name is Andrew! I’m a second-year PhD student in Biomedical Data Science at Stanford University, where I am advised by James Zou and supported by the NSF Graduate Research Fellowship. I am broadly interested in LLM agents and AI for Science/Medicine. I’m currently working on improving autonomous scientific discovery, focusing on making LLM agents more creative, better collaborators for scientists, and easier for humans to audit. I’m also interested in how best to align agents as they take on longer-horizon tasks.

Before Stanford, I was a research associate with Marinka Zitnik at Harvard Medical School, where I worked on evaluating whether protein language models reason evolutionarily and how well molecular AI models generalize. I was also a research fellow in the Summer Institute in Biomedical Informatics (SIBMI) program at HMS.

I received my MS in Artificial Intelligence from Northwestern University in 2024, where I was advised by Joshua Glaser, and my BS in Bioinformatics from UC San Diego in 2023, where I was advised by Melissa Gymrek. I’ve also been fortunate to be advised by Heather Moss and Kavita Sarin.

Get in touch

I’m always happy to chat about research or potential collaborations, so feel free to email me!

I’m also looking for motivated students with a strong computational background to work on LLM agents, evaluation, and AI for Science/Medicine. If you’re interested, please send me your resume.

Selected Papers

  1. Unlocking LLM Creativity in Science through Analogical Reasoning
    Andrew Shen, Shaul Druckmann, James Zou. Advances in Neural Information Processing Systems (NeurIPS), 2026.
  2. Evolutionary Reasoning Does Not Arise in Standard Usage of Protein Language Models
    Yasha Ektefaie*, Andrew Shen*, Lavik Jain, Maha Farhat, Marinka Zitnik. Advances in Neural Information Processing Systems (NeurIPS), 2025.
  3. Evaluating generalizability of artificial intelligence models for molecular datasets
    Yasha Ektefaie, Andrew Shen, Daria Bykova, Maximillian G. Marin, Marinka Zitnik, Maha Farhat. Nature Machine Intelligence, 2024.