2605.29522v1 May 28, 2026 cs.AI

DeepSurvey: Enhancing Analytical Depth and Citation Reliability in Automated Survey Generation

Da Ma
Da Ma
Citations: 469
h-index: 10
Lu Chen
Lu Chen
Citations: 460
h-index: 12
Kai Yu
Kai Yu
Citations: 542
h-index: 13
Hanqi Li
Hanqi Li
Citations: 44
h-index: 4
Yunzhe Zhang
Yunzhe Zhang
Citations: 41
h-index: 2
Ziyue Yang
Ziyue Yang
Citations: 23
h-index: 2
Zijian Hu
Zijian Hu
Scale AI
Citations: 345
h-index: 6
Tiancheng Huang
Tiancheng Huang
Citations: 50
h-index: 4
Chenrun Wang
Chenrun Wang
Citations: 113
h-index: 1
Xiaobao Wu
Xiaobao Wu
Citations: 189
h-index: 7
Zijian Wang
Zijian Wang
Citations: 4,581
h-index: 12

As scientific literature grows rapidly, automated survey generation has become a key capability for AI scientists and human researchers. However, existing systems suffer from limited analytical depth due to reliance on abstracts and isolated paper processing, and unreliable citations from imprecise retrieval and post-hoc grounding, producing superficial surveys and may mislead researchers. We present DeepSurvey, an agentic system that addresses both. To enhance depth, DeepSurvey extracts structured keynotes from full-text papers, models cross-paper relationships through clustering and comparative analysis, and integrates code-repository analysis to recover implementation-level details. To fortify reliability, it combines citation-graph expansion with hybrid filtering for topic-focussed retrieval, enforces evidence-constrained citation assignment, and deploys multi-granularity agentic refinement to validate citation-claim alignment. Experiments show that DeepSurvey achieves the highest content score (8.644/10) and citation quality (12.3% and 9.3% recall and precision gains over the strongest baseline), generalizes more robustly across domains (0.14 vs 0.22 to 0.69 CS-to-non-CS drop), and is preferred over human-written surveys by domain experts (83.3% overall quality, 100% content depth).

0 Citations
0 Influential
6.5 Altmetric
32.5 Score
Original PDF

No Analysis Report Yet

This paper hasn't been analyzed by Gemini yet.

Log in to request an AI analysis.

댓글

댓글을 작성하려면 로그인하세요.

아직 댓글이 없습니다. 첫 번째 댓글을 남겨보세요!