cs.CLNov 14, 2026

SurveyWeave: An Agentic Framework for Automated Survey Generation

Authors: Franklin Zhang, Xiao Yang, Xin Luna Dong, Juhua Hu

Organizations: University of Washington · Meta Reality Labs · University of Washington Tacoma

Abstract

Surveys help researchers keep up with fast-moving fields, but they take weeks to months to write. Automated survey generation (AutoSurvey) can alleviate this situation, but it is challenging to draw on hundreds to thousands of precisely scoped papers, choose among many valid structures, and stay faithful to its sources while offering insights. We present SurveyWeave, an agentic architecture that decomposes the problem into four tasks coordinated by three agents, each reviewing others' work and conducting revisions based on feedback. We also introduce WeaveEval, a five-dimension evaluation grounded in prior surveys. A comprehensive comparison shows that SurveyWeave outperforms Codex by 8 points and the strongest AutoSurvey baseline by 6 points.

Figures & tables

Appendix figures & tables9 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Deep Academic Survey: Stateful Agentic Closed-Loop Paradigm for Academic Survey Automation

    Aug 18, 2026Zhikai Xu, Zhucun Xue, Teng Hu +3Deep Research AgentsAgentic RAG

  2. SurveyAgent-HKA: A multi-agent framework for scientific survey generation with LLMs and human knowledge augmentation

    Sep 5, 2026Tong Bao, Mir Tafseer Nayeem, Yi Zhao +2AI-Assisted Scientific ResearchLLM Agents

  3. DeepSurvey: Agent-Oriented Automated Survey Generation with Analytical Depth and Citation Reliability

    May 28, 2026Ziyue Yang, Da Ma, Hanqi Li +8AI for ScienceAI Agents for Scientific Discovery