2 papers
cs.LG2026
TED: Training-Free Experience Distillation for Multimodal Reasoning
Shuozhi Yuan, Jinqing Wang, Zihao Liu +5
Knowledge distillation is typically realized by transferring a teacher model's knowledge into a student's parameters through supervised or reinforcement-based optimization. While e…
cs.CL2025
MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQL
Bing Wang, Changyu Ren, Jian Yang +8
Recent LLM-based Text-to-SQL methods usually suffer from significant performance degradation on "huge" databases and complex user questions that require multi-step reasoning. Moreo…