Diagnosing and Correcting Reward Hacking in Verifiable Instruction Following Paper • 2610.19525 • Published 7 days ago • 13
EvoDuet: Bilevel Co-Evolution of Web Searching and Task Solving for Scientific Discovery Paper • 2609.40340 • Published 22 days ago • 112
Domain Arithmetic: One-Shot VLA Adaptation under Environmental Shifts Paper • 2607.00666 • Published Jul 1 • 24