AutoSurvey2: Empowering Researchers with Next Level Automated Literature Surveys

TL;DR

AutoSurvey2 is an advanced automated system that generates comprehensive, accurate, and well-structured literature surveys by integrating retrieval, synthesis, and evaluation, significantly improving over existing methods.

Contribution

It introduces a multi-stage pipeline combining retrieval, structured synthesis, and multi-LLM evaluation for automated survey generation, advancing the state of automated scholarly writing.

Findings

Outperforms existing baselines in structural coherence and topical relevance.

Achieves higher evaluation scores in coverage, structure, and relevance.

Maintains strong citation fidelity in generated surveys.

Abstract

The rapid growth of research literature, particularly in large language models (LLMs), has made producing comprehensive and current survey papers increasingly difficult. This paper introduces autosurvey2, a multi-stage pipeline that automates survey generation through retrieval-augmented synthesis and structured evaluation. The system integrates parallel section generation, iterative refinement, and real-time retrieval of recent publications to ensure both topical completeness and factual accuracy. Quality is assessed using a multi-LLM evaluation framework that measures coverage, structure, and relevance in alignment with expert review standards. Experimental results demonstrate that autosurvey2 consistently outperforms existing retrieval-based and automated baselines, achieving higher scores in structural coherence and topical relevance while maintaining strong citation fidelity. By combining retrieval, reasoning, and automated evaluation into a unified framework, autosurvey2 provides a scalable and reproducible solution for generating long-form academic surveys and contributes a solid foundation for future research on automated scholarly writing. All code and resources are available at https://github.com/annihi1ation/auto_research.