AutoSurvey2: Empowering Researchers with Next Level Automated Literature Surveys

2025-10-29

AI Summary

To address the challenge of rapidly expanding literature in large language model (LLM) research—leading to delayed, incomplete survey papers—this work proposes the first fully automated, multi-stage system for generating comprehensive academic surveys. Methodologically, it integrates real-time retrieval-augmented generation (RAG), parallel chapter co-generation, structured multi-LLM evaluation, and iterative refinement to jointly optimize coverage, logical coherence, and citation fidelity. Key contributions include: (1) a verifiable, multi-dimensional automated quality assessment framework; and (2) support for dynamic literature updates alongside reproducible, extensible survey generation. Experimental results demonstrate significant improvements over existing baselines in structural coherence, topical relevance, and citation accuracy. This system establishes a novel paradigm for AI-assisted academic survey authoring.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Generation
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• Search and Retrieval-Augmented AI: Large language models for search
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

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.

Problem

• Automating comprehensive literature survey generation for researchers
• Addressing rapid growth of research publications with multi-stage pipeline
• Ensuring topical completeness and factual accuracy through automated evaluation

Innovation

• Multi-stage pipeline automates survey generation process
• Integrates parallel generation and iterative refinement techniques
• Uses multi-LLM evaluation framework for quality assessment