WhatWorkedBench: Benchmarking Experimental Understanding in AI Agents Paper • 2609.27490 • Published 9 days ago • 14
Scores Alone Do Not Prove Discovery: The Discovery Certification Protocol for Auditing AI Research Agents Paper • 2609.09219 • Published 25 days ago • 16
Auto Research with Specialist Agents Develops Effective and Non-Trivial Training Recipes Paper • 2605.05724 • Published May 7 • 16
ODesign: A World Model for Biomolecular Interaction Design Paper • 2510.22304 • Published Oct 25, 2025 • 23