Agentic on-policy distillation implicitly reshapes ReAct patterns and causes negative transfer

Deyang Kong · hf · 2026-11-18

A study from PKU, USTC, Tsinghua and Zhejiang University examines how on-policy distillation (OPD) implicitly reshapes LLM agents' ReAct interaction patterns across math, ALFWorld, and τ²-bench:

Original post →

More from coding & agent

coding & agent channel →