研究人员开发了一种新的AI代理训练方法——重放前缀策略内蒸馏（ReOPD）。该技术通过重用预先收集的教师轨迹作为前缀，解决了传统策略内蒸馏的高成本问题。ReOPD缓解了“前缀陷阱”，即学生策略的改进可能导致教师监督不可靠。该方法在数学推理和搜索任务中显示出有效性，达到了与现有方法相当的准确率，同时速度显著更快，并且在学生训练期间不需要工具调用。 AI
影响 通过重用交互数据，实现了更具可扩展性和效率的AI代理训练。
排序理由 这是一篇详细介绍AI代理训练新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
arXiv:2607.04037v1 Announce Type: cross Abstract: On-policy distillation is a powerful way to transfer reasoning ability from a strong teacher to a smaller student: the student samples trajectories from its own policy, and the teacher provides dense token-level supervision on the…
arXiv:2607.04763v1 Announce Type: cross Abstract: We study on-policy distillation (OPD) for agentic tasks, where an LLM agent interacts with an environment over multiple turns and a student imitates a teacher over these multi-turn interaction histories. Fully online OPD is costly…
We study on-policy distillation (OPD) for agentic tasks, where an LLM agent interacts with an environment over multiple turns and a student imitates a teacher over these multi-turn interaction histories. Fully online OPD is costly because each update requires fresh student rollou…