MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQL

arXiv:2312.11242v3 Announce Type: replace
Abstract: 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. Moreover, most existing methods neglect the crucial significance of LLMs utilizing external tools and model collaboration. To address these challenges, we introduce MAC-SQL, a novel LLM-based multi-agent collaborative framework. Our framework comprises a core decomposer agent for Text-to-SQL generation with few-shot chain-of-thought reasoning, accompanied by two auxiliary agents that utilize external tools or models …

agent arxiv collaborative cs.cl framework mac multi-agent sql text text-to-sql type