Self-Retrospection Distillation: Turning Post-hoc Experiences into Prior Foresight Paper • 2610.08077 • Published 12 days ago • 194
The Illusion of Certainty: Decoupling Capability and Calibration in On-Policy Distillation Paper • 2604.16830 • Published Apr 18 • 15
MCPEval: Automatic MCP-based Deep Evaluation for AI Agent Models Paper • 2507.12806 • Published Jul 17, 2025 • 21