研究人员开发了SAGE-OPD，一种用于多轮按策略蒸馏（OPD）的新型框架，旨在改进语言模型智能体的训练。与之前专注于单轮设置的方法不同，SAGE-OPD通过基于教师判断和置信度选择性地干预学生响应，解决了多轮交互中累积错误的问题。实验表明，SAGE-OPD取得了显著的改进，包括在ALFWorld基准测试上成功率相对提高高达13.3%。 AI
影响 这项研究通过提高训练效率和减轻常见错误，可能带来更强大、更有能力的ವರೆಗೆ多轮语言模型智能体。
排序理由 该集群包含一篇详细介绍AI模型训练新方法的论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2606.19659v1 Announce Type: new Abstract: On-policy distillation (OPD) improves student models by training them on trajectories induced by their own policy, making it a promising approach for mitigating exposure bias in agent training. However, most OPD studies focus on sin…
On-policy distillation (OPD) improves student models by training them on trajectories induced by their own policy, making it a promising approach for mitigating exposure bias in agent training. However, most OPD studies focus on single-turn settings, while realistic LLM agents in…