Student-Centered Distillation Narrows the Agentic Gap Between Small and Large LLMs
以学生为中心的蒸馏缩小了小型和大型语言模型之间的智能差距
机构 * University of Science and Technology of China(中国科学技术大学)
专题命中 工具调用 :agentic(title,abstract);tool-use(abstract);分类 cs.AI、cs.CL
AI总结 研究旨在缩小大小语言模型智能差距,提出SCoRe框架,让学生生成训练轨迹,教师纠正最早错误,经微调与短视距强化学习,提升学生解决问题能力,在12个基准测试中,70亿参数学生模型缩小了与720亿参数教师模型的性能差距
Comments Accepted to ICML 2026. The title has been changed from "From Correction to Mastery: Reinforced Distillation of Large Language Model Agents" to "Student-Centered Distillation Narrows the Agentic Gap Between Small and Large LLMs"; the camera-ready version has been uploaded