TrigReason: Trigger-Based Collaboration between Small and Large Reasoning Models
TrigReason:基于触发的大小推理模型协作
机构 * AGI Institute, School of Computer Science, Shanghai Jiao Tong University, Shanghai, China(AGI研究院,计算机科学学院,上海交通大学,上海,中国) ; Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering, Shanghai Jiao Tong University, Shanghai, China(上海市教育委员会智能交互与认知工程重点实验室,上海交通大学,上海,中国) ; Shanghai Key Laboratory for Intelligent Information Processing, Fudan University(上海市智能信息处理重点实验室,复旦大学) ; State Key Laboratory for Novel Software Technology, Nanjing University(新型软件技术国家重点实验室,南京大学) ; School of Artificial Intelligence, Wuhan University(人工智能学院,武汉大学) ; Institute of Computer Science, University of Göttingen, Göttingen, Germany(计算机科学研究所,哥廷根大学,哥廷根,德国)
专题命中 复杂问题求解 :reasoning(title,abstract);planning(abstract);分类 cs.AI
AI总结 本文提出TrigReason框架,通过触发机制将大部分推理任务交给小型模型,仅在必要时调用大模型,提升推理效率与准确性。
Comments ACL 2026 Findings