Bhavana Dalvi Mishra

Lead Reserarch Scientist, Allen Institute for Artificial Intelligence

1 paper at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 5

Friday, December 5, 2025 · 11:00 AM → 2:00 PM

AutoDiscovery: Open-ended Scientific Discovery via Bayesian Surprise

#1610 · Dhruv Agarwal, Bodhisattwa Prasad Majumder, Reece Adamson, Megha Chakravorty, Satvika Reddy Gavireddy, Aditya Parashar, Harshit Surana, Bhavana Dalvi Mishra, Andrew McCallum, Ashish Sabharwal, Peter Clark

We present AutoDiscovery, a method for open-ended scientific discovery that uses Bayesian surprise and Monte Carlo tree search to sample diverse hypotheses at scale that are likely to lead to discoveries that are suprising both to LLMs and humans.