Self-Retrospection Distillation: Turning Post-hoc Experiences into Prior Foresight
Paper • 2610.08077 • Published • 194
Interesting Papers
-
-
Prospective Hindsight: Self-Calibrating Reinforcement Learning via Prediction-Reality Gaps
Paper • 2610.02740 • Published • 11 -
Initialization Improves LLM-Driven Discovery
Paper • 2610.00707 • Published • 6 -
Relevance Does Not Imply Applicability: Experience Activation for Personal GUI Agents
Paper • 2609.33304 • Published • 44 -
Scaling Agentic Data for Long-Horizon Terminal Intelligence
Paper • 2610.13166 • Published • 161