跳到正文
原文
arXiv cs.AI· O. Ozan Koyluoglu·· 5 小时前AI 评分42

Hindsight Structured Advice Distillation 如何提升 Executor Agents 表现

Hindsight Structured Advice Distillation: Steering Executor Agents with Advisors Trained on Their Failures and Task Characteristics

AI 摘要

研究提出 hindsight structured advice distillation (HSAD) 方法,通过小型 advisor 模型生成结构化建议来引导 executor agents。

来源:arXiv cs.AI · arxiv.org