Trust Functions: Near-Lossless Weak-to-Strong Generalization by Learning When to Trust the Weak Teacher Paper • 2606.01000 • Published May 31 • 7
AgentOdyssey: Open-Ended Long-Horizon Text Game Generation for Test-Time Continual Learning Agents Paper • 2606.24893 • Published May 29 • 9
Continual Learning Mechanisms Compose for Long-Horizon Memorization Paper • 2609.06986 • Published 27 days ago • 376