Deep Academic Survey: Stateful Agentic Closed-Loop Paradigm for Academic Survey Automation
2026-08-18 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors present DAS, a new system designed to help create academic surveys by organizing and summarizing large amounts of research papers more effectively. Unlike previous tools, DAS keeps track of paper analysis and manuscript writing separately, making the process more organized and easier to update. They built DAS using a large database of about two million papers and developed special methods for planning, citing, and reviewing content. Their evaluations show that DAS outperforms other similar systems in creating well-structured, properly cited academic surveys. They also created benchmarks and evaluation tools to measure the quality of survey generation.
academic surveyliterature reviewmanuscript assemblycitation planningmetadata laketaxonomy planningsemantic reviewbenchmark evaluationhierarchical discourseresearch automation
Authors
Zhikai Xu, Zhucun Xue, Teng Hu, Yabiao Wang, Yong Liu, Jiangning Zhang
Abstract
Academic surveys play a central role in organizing rapidly expanding scholarly literature, yet their construction requires extensive paper analysis, coherent knowledge organization, fine-grained citation support, and reliable manuscript assembly. Existing Deep Research and automated survey generation systems address parts of this process, but typically do not coordinate paper understanding, literature organization, evidence-grounded drafting, and manuscript validation through a shared, revisable state. We introduce DAS, a stateful agentic framework for generating publication-oriented academic surveys. Its key idea is to separate reusable paper analysis from topic-specific manuscript construction. DAS builds on DAS-2M, a dynamically updated metadata lake containing survey-oriented representations of approximately two million papers. Its agents maintain explicit literature, organization, writing, and finalization states through candidate-grounded taxonomy planning, reverse paper-to-section routing, and hierarchical claim and citation planning. Semantic review reactivates only the affected writing states for repair and reevaluation, forming a scoped closed loop with deterministic validation. We further introduce DAS-Bench, a 30-topic benchmark, together with DAS-Eval, which assesses scholarly citation quality, taxonomic synthesis, hierarchical discourse, and manuscript assembly reliability through 16 criteria. Among systems evaluated on all 30 topics, DAS achieves the highest average in all four dimensions, with an overall score of 4.34 compared with 4.03 for the strongest competitor, and the same ordering is preserved on the matched 21-topic CS subset. Blinded expert evaluation further prefers DAS to Naive RAG on 27 of 30 topics and to AutoSurvey on 19 of 21 shared CS topics. The project page is available at https://zhikaixu24.github.io/projects/DAS/.