AutoSurvey: Large Language Models Can Automatically Write Surveys

By Yidong Wang, Qi Guo, Wenjin Yao, Hongbo Zhang, Xin Zhang, Zhen Wu, Meishan Zhang, Xin-Yu Dai, Min Zhang, Qing-Song Wen and 3 more. 2024

Subfields: Large Language Models, LLM Agents & Tool Use, Natural Language Generation

Citations in the corpus

• AutoSurvey2: Empowering Researchers with Next Level Automated Literature Surveys (2025, unknown): “AutoSurvey (Wang et al., 2024b) introduced a structured pipeline for LLM-driven survey generation to address the exploding volume of publications in rapidly evolving fields.”
• Deep Literature Survey Automation with an Iterative Workflow (2025, unknown): “This approach is evident in pipeline-based systems like AutoSurvey (Wang et al., 2024b), which employs a hierarchical paradigm, and SurveyForge (Yan et al., 2025), which utilizes a memory-driven scholar navigation agent.”
• InteractiveSurvey: An LLM-based Personalized and Interactive Survey Paper Generation System (2025, unknown): “Evaluation Metrics Following existing survey generation systems (Wang et al., 2024b; Liang et al., 2025), we employ LLMs as judges (Li et al., 2024a) to assess the survey papers in Coverage : the extent to which the survey encapsulates all aspects of the topic; Structure : the logical organization…”
• Bloom-Eval: A Hierarchical Evaluation Benchmark for Automatic Survey Generation Based on Bloom's Taxonomy (2026, unknown): “For instance, AutoSurvey (Wang et al., 2024a) employs LLMs to assess aspects like citation quality and content relevance.”