Hugging Face Papers ↗ · 2026-11-14
Agentic On-Policy Distillation Implicitly Reshapes LLMs' ReAct Patterns
媒体报道 Hugging Face Papers 原文语言:中文
论文摘要(作者报告,未经本站复测):On-policy distillation (OPD) transfers specialized capabilities to language-model agents, but its cross-domain effects on interaction remain unclear.
全文
On-policy distillation can improve or degrade language-model agent interaction across domains, and selectively retaining teacher-preferred positions mitigates negative transfer at a cost to source-domain learning.
正文以来源语言显示。