TimeBill: Time-Budgeted Inference for Large Language Models Paper • 2512.21859 • Published 6 days ago • 18
Nested Browser-Use Learning for Agentic Information Seeking Paper • 2512.23647 • Published 3 days ago • 11
Emergent temporal abstractions in autoregressive models enable hierarchical reinforcement learning Paper • 2512.20605 • Published 9 days ago • 59
Reinforcement Learning for Self-Improving Agent with Skill Library Paper • 2512.17102 • Published 13 days ago • 29