Aug 2026· arXiv.org· Vol abs/2608.18034· 0 citations· 70 references
Computer Science
TL;DR
DAS is introduced, a stateful agentic framework for generating publication-oriented academic surveys to separate reusable paper analysis from topic-specific manuscript construction, and 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.
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/.
Most retrieval-augmented systems treat literature search as a single retrieval step followed by summarization. Real literature research works differently: the investigator's understanding of the question changes as they read, new subquestions appear, and evidence is weighed, not just collected. We present Optimist Deep...
Scientific agents must connect research problems, methods, and findings dispersed through narrative articles. We introduce SPRA (Structured Paper Representation for Agents), a paper-level representation of persistent research objects and typed relations. Its empirical-AI profile organizes Problems, Contributions, Compo...
Yu-Tong Leng, Hao-Jiong Chen, Fu-Kai Shang et al.· 0 citations
LongCat-DeepResearch is presented, a deep research system that combines an enhanced LongCat model with a multi-agent workflow for producing comprehensive, evidence-grounded reports and improves average automatic readability preference across two benchmarks, with different trends on each.
He Zhu, Yue-Ya Xu, Wan-Li Wu et al.· arXiv.org· 0 citations
The growing volume of scientific literature has made research-paper analysis increasingly time-consuming for students, researchers, and academicians. Tasks such as literature review generation, methodology understanding, research gap identification, citation formatting, and trend discovery often require substantial man...
S. Chaudhari, Akansha Mahore, Tanmay Ranotkar et al.· International Journal of Cre...· 0 citations
INSPIRE, a benchmark for evaluating agents that search prior literature to make progress on solution-redacted research problems, enables both end-to-end comparison and stage-resolved diagnosis in a setting where the agent must construct its own working criterion of relevance.
Most automated survey generation systems retrieve papers as flat documents, limiting their ability to capture research structure. We present SurveyGraph, a framework built around a Methods-Entity Knowledge Graph (MEKG) encoding method-level follow-on, competition, and shared-resource relations. The graph supports core-...
Yi-Fan Yuan, Yan-Cheng Zhu, Zuo-Yu Zhang et al.· Conference on Empirical Meth...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.