Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe Paper • 2604.13016 • Published Apr 14 • 106
CreativityBench: Evaluating Agent Creative Reasoning via Affordance-Based Tool Repurposing Paper • 2605.02910 • Published 17 days ago • 22
UserRL: Training Interactive User-Centric Agent via Reinforcement Learning Paper • 2509.19736 • Published Sep 24, 2025 • 12
UserBench: An Interactive Gym Environment for User-Centric Agents Paper • 2507.22034 • Published Jul 29, 2025 • 30