Author

Can Xie

h-index 7 View on Semantic Scholar

We have 1 of 15 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Aug 2026

EDGE: Experience-Distillation for Guided Exploration in Agentic Reinforcement Learning

This work proposes EDGE (Experience-Distillation for Guided Exploration), a framework that treats retrieved experiences as temporary training-time scaffolds and progressively internalizes their benefits into the parametric policy.

Can Xie, Yu-Yi Zhou, Wen Yang et al. · 1 citation