作者位次 #2/5ACL 2026Findings· Findings of ACL
Failures are Treasures: Constructing a Pedagogical Bridge for Agentic Strategy Distillation
Jiaxin Guo · Hao Sun · Wenhao Zhang · Chunyu Yang · Yan Zhang
摘要
While Large Language Models (LLMs) excel in autonomous agent settings, small language models (SLMs) remain fragile, often collapsing after encountering errors. Traditional knowledge distillation focuses on imitating successful trajectories, while existing “learning from mistakes” methods treat er...