This paper introduces AutoSurvey, a methodology that leverages large language models (LLMs) to automate the creation of comprehensive literature surveys in rapidly evolving fields like artificial intelligence. Traditional survey paper creation faces challenges due to the vast volume and complexity of information, prompting the need for efficient methods. While LLMs offer promise, they are constrained by context window limitations, parametric knowledge, and lack of evaluation benchmarks. AutoSurvey addresses these challenges through a systematic approach involving initial retrieval, outline generation, subsection drafting by specialized LLMs, integration and refinement, and rigorous evaluation and iteration. The contributions include a comprehensive solution, a reliable evaluation method, and experimental validation demonstrating AutoSurvey's effectiveness. The system is open-source and aims to provide a scalable and effective solution for synthesizing research literature.This paper introduces AutoSurvey, a methodology that leverages large language models (LLMs) to automate the creation of comprehensive literature surveys in rapidly evolving fields like artificial intelligence. Traditional survey paper creation faces challenges due to the vast volume and complexity of information, prompting the need for efficient methods. While LLMs offer promise, they are constrained by context window limitations, parametric knowledge, and lack of evaluation benchmarks. AutoSurvey addresses these challenges through a systematic approach involving initial retrieval, outline generation, subsection drafting by specialized LLMs, integration and refinement, and rigorous evaluation and iteration. The contributions include a comprehensive solution, a reliable evaluation method, and experimental validation demonstrating AutoSurvey's effectiveness. The system is open-source and aims to provide a scalable and effective solution for synthesizing research literature.