DRIFT: Decoupled Rollouts and Importance-Weighted Fine-Tuning for Efficient Multi-Turn Optimization Paper • 2605.31455 • Published May 29 • 7
COBRA-Skills: Contextual Bandit-Guided Evolution for Agent Skill Optimization Paper • 2609.11682 • Published 5 days ago • 29
COBRA-Skills: Contextual Bandit-Guided Evolution for Agent Skill Optimization Paper • 2609.11682 • Published 5 days ago • 29
SPOT: Sparse Probing and Outcome Calibration for On-Policy Distillation Paper • 2608.04419 • Published Aug 5 • 29
COBRA-Skills: Contextual Bandit-Guided Evolution for Agent Skill Optimization Paper • 2609.11682 • Published 5 days ago • 29