# Deep Literature Survey Automation with an Iterative Workflow

arXiv: https://arxiv.org/abs/2510.21900 · HTML: https://mlsanity.com/paper/2510.21900/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 51 references that are in the map.
- First posted on arXiv 24 Oct 2025.

## Builds on (most cited first, 23 of 23)

- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference](https://mlsanity.com/paper/2403.04132/) (2024)
- [Enabling Large Language Models to Generate Text with Citations](https://mlsanity.com/paper/2305.14627/) (2023)
- [Multi-News: a Large-Scale Multi-Document Summarization Dataset and Abstractive Hierarchical Model](https://mlsanity.com/paper/1906.01749/) (2019)
- [MinerU: An Open-Source Solution for Precise Document Content Extraction](https://mlsanity.com/paper/2409.18839/) (2024)
- [Nomic Embed: Training a Reproducible Long Context Text Embedder](https://mlsanity.com/paper/2402.01613/) (2024)
- [Proving Test Set Contamination in Black Box Language Models](https://mlsanity.com/paper/2310.17623/) (2023)
- [Rethinking Benchmark and Contamination for Language Models with Rephrased Samples](https://mlsanity.com/paper/2311.04850/) (2023)
- [PullNet: Open Domain Question Answering with Iterative Retrieval on Knowledge Bases and Text](https://mlsanity.com/paper/1904.09537/) (2019)
- [TLDR: Extreme Summarization of Scientific Documents](https://mlsanity.com/paper/2004.15011/) (2020)
- [AutoSurvey: Large Language Models Can Automatically Write Surveys](https://mlsanity.com/paper/2406.10252/) (2024)
- [Split and Merge: Aligning Position Biases in LLM-based Evaluators](https://mlsanity.com/paper/2310.01432/) (2023)
- [RankME: Reliable Human Ratings for Natural Language Generation](https://mlsanity.com/paper/1803.05928/) (2018)
- [The AI Review Lottery: Widespread AI-Assisted Peer Reviews Boost Paper Scores and Acceptance Rates](https://mlsanity.com/paper/2405.02150/) (2024)
- [SurveyForge: On the Outline Heuristics, Memory-Driven Generation, and Multi-dimensional Evaluation for Automated Survey Writing](https://mlsanity.com/paper/2503.04629/) (2025)
- [Query expansion techniques for information retrieval: A survey](https://mlsanity.com/paper/1708.00247/) (2017)
- [EvolveSearch: An Iterative Self-Evolving Search Agent](https://mlsanity.com/paper/2505.22501/) (2025)
- [SurveyX: Academic Survey Automation via Large Language Models](https://mlsanity.com/paper/2502.14776/) (2025)
- [From Replication to Redesign: Exploring Pairwise Comparisons for LLM-Based Peer Review](https://mlsanity.com/paper/2506.11343/) (2025)
- [Deep Reinforced Query Reformulation for Information Retrieval](https://mlsanity.com/paper/2007.07987/) (2020)
- [Reducing Distraction in Long-Context Language Models by Focused Learning](https://mlsanity.com/paper/2411.05928/) (2024)
- [SWE-Arena: An Interactive Platform for Evaluating Foundation Models in Software Engineering](https://mlsanity.com/paper/2502.01860/) (2025)

## Built on by (most cited first, 7 of 7)

- [AI for Auto-Research: Roadmap & User Guide](https://mlsanity.com/paper/2605.18661/) (2026)
- [AutoSurvey2: Empowering Researchers with Next Level Automated Literature Surveys](https://mlsanity.com/paper/2510.26012/) (2025)
- [Can AI Review Improve Paper Drafting? An Empirical Study on 20 Computer Architecture Submissions](https://mlsanity.com/paper/2606.01013/) (2026)
- [Making AI Scientists Auditable from Evidence to Claim](https://mlsanity.com/paper/2606.18874/) (2026)
- [OUTLINEFORGE: Hierarchical Reinforcement Learning with Explicit States for Scientific Writing](https://mlsanity.com/paper/2601.09858/) (2026)
- [AiraXiv: An AI-Driven Open-Access Platform for Human and AI Scientists](https://mlsanity.com/paper/2605.21481/) (2026)
- [Deep Academic Survey: Stateful Agentic Closed-Loop Paradigm for Academic Survey Automation](https://mlsanity.com/paper/2608.18034/) (2026)

## Abstract (arXiv)

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/IterSurveyAutosurveyv2.