Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Deep Literature Survey Automation with an Iterative Workflow

Hongbo Zhang, Han Cui, Yidong Wang, Yijian Tian, Qi Guo, Cunxiang Wang, Jian Wu, Chiyu Song, Yue Zhang

TL;DR

IterSurvey tackles limitations of one-shot automated survey generation by introducing a recurrent outline generation paradigm that updates the outline as it reads more papers. It uses paper cards to ground each citation and a reviewer–refiner loop to ensure coherence and multimodal visualization. It also introduces Survey-Arena, a pairwise benchmark to compare machine-generated surveys against human-written exemplars, demonstrating improvements in structure, coverage, and citation quality across topics. Code and data are released to enable reproducibility and further development.

Abstract

Automatic literature survey generation has attracted increasing attention, yet most existing systems follow a one-shot paradigm, where a large set of papers is retrieved at once and a static outline is generated before drafting. This design often leads to noisy retrieval, fragmented structures, and context overload, ultimately limiting survey quality. Inspired by the iterative reading process of human researchers, we propose \ours, a framework based on recurrent outline generation, in which a planning agent incrementally retrieves, reads, and updates the outline to ensure both exploration and coherence. To provide faithful paper-level grounding, we design paper cards that distill each paper into its contributions, methods, and findings, and introduce a review-and-refine loop with visualization enhancement to improve textual flow and integrate multimodal elements such as figures and tables. Experiments on both established and emerging topics show that \ours\ substantially outperforms state-of-the-art baselines in content coverage, structural coherence, and citation quality, while producing more accessible and better-organized surveys. To provide a more reliable assessment of such improvements, we further introduce Survey-Arena, a pairwise benchmark that complements absolute scoring and more clearly positions machine-generated surveys relative to human-written ones. The code is available at https://github.com/HancCui/IterSurvey\_Autosurveyv2.

Deep Literature Survey Automation with an Iterative Workflow

TL;DR

IterSurvey tackles limitations of one-shot automated survey generation by introducing a recurrent outline generation paradigm that updates the outline as it reads more papers. It uses paper cards to ground each citation and a reviewer–refiner loop to ensure coherence and multimodal visualization. It also introduces Survey-Arena, a pairwise benchmark to compare machine-generated surveys against human-written exemplars, demonstrating improvements in structure, coverage, and citation quality across topics. Code and data are released to enable reproducibility and further development.

Abstract

Automatic literature survey generation has attracted increasing attention, yet most existing systems follow a one-shot paradigm, where a large set of papers is retrieved at once and a static outline is generated before drafting. This design often leads to noisy retrieval, fragmented structures, and context overload, ultimately limiting survey quality. Inspired by the iterative reading process of human researchers, we propose \ours, a framework based on recurrent outline generation, in which a planning agent incrementally retrieves, reads, and updates the outline to ensure both exploration and coherence. To provide faithful paper-level grounding, we design paper cards that distill each paper into its contributions, methods, and findings, and introduce a review-and-refine loop with visualization enhancement to improve textual flow and integrate multimodal elements such as figures and tables. Experiments on both established and emerging topics show that \ours\ substantially outperforms state-of-the-art baselines in content coverage, structural coherence, and citation quality, while producing more accessible and better-organized surveys. To provide a more reliable assessment of such improvements, we further introduce Survey-Arena, a pairwise benchmark that complements absolute scoring and more clearly positions machine-generated surveys relative to human-written ones. The code is available at https://github.com/HancCui/IterSurvey\_Autosurveyv2.
Paper Structure (40 sections, 9 equations, 7 figures, 9 tables, 1 algorithm)

This paper contains 40 sections, 9 equations, 7 figures, 9 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Related Work
  3. Automated Survey Generation
  4. Evaluation of Automated Surveys
  5. IterSurvey
  6. Recurrent Outline Generation
  7. Paper Card Pool.
  8. Outline updating.
  9. Keyword expansion.
  10. Stopping condition.
  11. Post-processing.
  12. Section Drafting Guided by Paper Cards
  13. Global Review and Integration
  14. Textual Review-and-Refine.
  15. Figure–Table Integration.
  16. ...and 25 more sections

Figures (7)

  • Figure 1: Overview of IterSurvey and Survey-Arena.
  • Figure 2: LLM-generated survey comparison between AutoSurvey and IterSurvey.
  • Figure 3: Elo scores of Survey-Arena results across topics. The radar plot shows the Elo scores for each system across all topics, providing a topic-wise comparison.
  • Figure 4: LLM-generated survey comparison between AutoSurvey and IterSurvey.
  • Figure 5: LLM-generated survey comparison between AutoSurvey and IterSurvey.
  • ...and 2 more figures