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

• URL: http://arxiv.org/abs/2605.29522v1
• Date: Thu, 28 May 2026 07:40:10 GMT
• Title: DeepSurvey: Enhancing Analytical Depth and Citation Reliability in Automated Survey Generation
• Abstract summary: DeepSurvey extracts structured keynotes from full-text papers, models cross-paper relationships through clustering and comparative analysis.<n>It enforces evidence-constrained citation assignment, and deploys multi-granularity agentic refinement to validate citation-claim alignment.<n>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)
• Score: 27.73022251076876
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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).

Related papers

• Mr.LHDR: A Benchmark for Multimodal Real-World Long-Horizon Deep Research Agents [72.19038675107662]
  Mr. L is a benchmark for evaluating real-world deep research over long, irreducible chains of verifiable evidence.<n>Each question is constructed from a hidden Node-Relation graph and requires an average of 12.1 necessary intermediate conclusions.
  arXiv  Detail & Related papers  (2026-09-10T09:47:44Z)
• AutoResearchBench: Benchmarking AI Agents on Complex Scientific Literature Discovery [55.70879973230979]
  AutoResearchBench is a benchmark for autonomous scientific literature discovery.<n>Compared to previous benchmarks on agentic web browsing, AutoResearchBench is research-oriented.<n>Even the most powerful LLMs, despite having largely conquered general agentic web-browsing benchmarks such as BrowseComp, achieve only 9.39% accuracy on Deep Research and 9.31% IoU on Wide Research.
  arXiv  Detail & Related papers  (2026-04-28T06:05:17Z)
• Can Deep Research Agents Find and Organize? Evaluating the Synthesis Gap with Expert Taxonomies [57.11324429385405]
  We introduce TaxoBench, a diagnostic benchmark derived from 72 computer science surveys.<n>We manually extract expert-authored taxonomy trees containing 3,815 precisely categorized citations as ground truth.<n>Best agent recalls only 20.9% of expert-selected papers, and even with perfect input, the best model achieves only 0.31 ARI in organization.
  arXiv  Detail & Related papers  (2026-01-18T11:57:09Z)
• AutoMalDesc: Large-Scale Script Analysis for Cyber Threat Research [81.04845910798387]
  Generating natural language explanations for threat detections remains an open problem in cybersecurity research.<n>We present AutoMalDesc, an automated static analysis summarization framework that operates independently at scale.<n>We publish our complete dataset of more than 100K script samples, including annotated seed (0.9K) datasets, along with our methodology and evaluation framework.
  arXiv  Detail & Related papers  (2025-11-17T13:05:25Z)
• SQuAI: Scientific Question-Answering with Multi-Agent Retrieval-Augmented Generation [4.224843546370802]
  SQuAI is a scalable and trustworthy multi-agent retrieval-augmented generation framework for scientific question answering.<n>Built on over 2.3 million full-text papers from arXiv.org, SQuAI employs four collaborative agents to decompose complex questions into sub-questions.<n>Our system improves faithfulness, answer relevance, and contextual relevance by up to +0.088 (12%) over a strong RAG baseline.
  arXiv  Detail & Related papers  (2025-10-17T14:20:55Z)
• Span-level Detection of AI-generated Scientific Text via Contrastive Learning and Structural Calibration [2.105564340986074]
  Sci-SpanDet is a structure-aware framework for detecting AI-generated scholarly texts.<n>It combines section-conditioned stylistic modeling with multi-level contrastive learning to capture human nuanced-AI differences.<n>It achieves state-of-the-art performance, with F1(AI) of 80.17, AUROC of 92.63, and Span-F1 of 74.36.
  arXiv  Detail & Related papers  (2025-10-01T13:35:14Z)
• DeepTRACE: Auditing Deep Research AI Systems for Tracking Reliability Across Citations and Evidence [50.97612134791782]
  Generative search engines and deep research LLM agents promise trustworthy, source-grounded synthesis, yet users regularly encounter overconfidence, weak sourcing, and confusing citation practices.<n>We introduce DeepTRACE, a novel sociotechnically grounded audit framework that turns prior community-identified failure cases into eight measurable dimensions spanning answer text, sources, and citations.
  arXiv  Detail & Related papers  (2025-09-02T00:32:38Z)
• HySemRAG: A Hybrid Semantic Retrieval-Augmented Generation Framework for Automated Literature Synthesis and Methodological Gap Analysis [55.2480439325792]
  HySemRAG is a framework that combines Extract, Transform, Load (ETL) pipelines with Retrieval-Augmented Generation (RAG)<n>System addresses limitations in existing RAG architectures through a multi-layered approach.
  arXiv  Detail & Related papers  (2025-08-01T20:30:42Z)
• DeepResearch$^{\text{Eco}}$: A Recursive Agentic Workflow for Complex Scientific Question Answering in Ecology [0.0]
  DeepResearch is a novel agentic LLM-based system for automated scientific synthesis.<n>It supports depth- and breadth-controlled exploration of original research questions.<n>DeepResearch achieves up to a 21-fold increase in source integration.
  arXiv  Detail & Related papers  (2025-07-14T17:47:28Z)
• Benchmarking Deep Search over Heterogeneous Enterprise Data [73.55304268238474]
  We present a new benchmark for evaluating a form of retrieval-augmented generation (RAG)<n>RAG requires source-aware, multi-hop reasoning over diverse, sparsed, but related sources.<n>We build it using a synthetic data pipeline that simulates business across product planning, development, and support stages.
  arXiv  Detail & Related papers  (2025-06-29T08:34:59Z)
• SciSage: A Multi-Agent Framework for High-Quality Scientific Survey Generation [2.985620880452744]
  SciSage is a multi-agent framework employing a reflect-when-you-write paradigm.<n>It critically evaluates drafts at outline, section, and document levels, collaborating with specialized agents for query interpretation, content retrieval, and refinement.<n>We also release SurveyScope, a benchmark of 46 high-impact papers ( 2020-2025) across 11 computer science domains.
  arXiv  Detail & Related papers  (2025-06-15T02:23:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.