# SurveyGen-I: Consistent Scientific Survey Generation with Evolving Plans and Memory-Guided Writing

arXiv: https://arxiv.org/abs/2508.14317 · HTML: https://mlsanity.com/paper/2508.14317/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 43 references that are in the map.
- First posted on arXiv 20 Aug 2025.

## Builds on (most cited first, 19 of 19)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [MPNet: Masked and Permuted Pre-training for Language Understanding](https://mlsanity.com/paper/2004.09297/) (2020)
- [C-Pack: Packed Resources For General Chinese Embeddings](https://mlsanity.com/paper/2309.07597/) (2023)
- [LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods](https://mlsanity.com/paper/2412.05579/) (2024)
- [Nomic Embed: Training a Reproducible Long Context Text Embedder](https://mlsanity.com/paper/2402.01613/) (2024)
- [Formal Verification of Piece-Wise Linear Feed-Forward Neural Networks](https://mlsanity.com/paper/1705.01320/) (2017)
- [Chain of Agents: Large Language Models Collaborating on Long-Context Tasks](https://mlsanity.com/paper/2406.02818/) (2024)
- [Construction of the Literature Graph in Semantic Scholar](https://mlsanity.com/paper/1805.02262/) (2018)
- [Chain of Ideas: Revolutionizing Research Via Novel Idea Development with LLM Agents](https://mlsanity.com/paper/2410.13185/) (2024)
- [LitLLM: A Toolkit for Scientific Literature Review](https://mlsanity.com/paper/2402.01788/) (2024)
- [SurveyForge: On the Outline Heuristics, Memory-Driven Generation, and Multi-dimensional Evaluation for Automated Survey Writing](https://mlsanity.com/paper/2503.04629/) (2025)
- [ChatCite: LLM Agent with Human Workflow Guidance for Comparative Literature Summary](https://mlsanity.com/paper/2403.02574/) (2024)
- [SciReviewGen: A Large-scale Dataset for Automatic Literature Review Generation](https://mlsanity.com/paper/2305.15186/) (2023)
- [Abstraction and Refinement: Towards Scalable and Exact Verification of Neural Networks](https://mlsanity.com/paper/2207.00759/) (2022)
- [Gradient Weight-normalized Low-rank Projection for Efficient LLM Training](https://mlsanity.com/paper/2412.19616/) (2024)
- [Instruct Large Language Models to Generate Scientific Literature Survey Step by Step](https://mlsanity.com/paper/2408.07884/) (2024)
- [Automated Literature Review Using NLP Techniques and LLM-Based Retrieval-Augmented Generation](https://mlsanity.com/paper/2411.18583/) (2024)
- [Patience is all you need! An agentic system for performing scientific literature review](https://mlsanity.com/paper/2504.08752/) (2025)
- [Facets, Taxonomies, and Syntheses: Navigating Structured Representations in LLM-Assisted Literature Review](https://mlsanity.com/paper/2504.18496/) (2025)

## Built on by (most cited first, 5 of 5)

- [DeepSurvey-Bench: Evaluating Academic Value of Automatically Generated Scientific Surveys](https://mlsanity.com/paper/2601.15307/) (2026)
- [Agentic AI-Empowered Dynamic Survey Framework](https://mlsanity.com/paper/2602.04071/) (2026)
- [ScaffoldAgent: Utility-Guided Dynamic Outline Optimization for Open-Ended Deep Research](https://mlsanity.com/paper/2606.20122/) (2026)
- [What Can a Leaderboard Certify? Compositional Controllability for Fair Evaluation and Training of Biomedical Literature-Review Agents](https://mlsanity.com/paper/2609.32318/) (2026)
- [Beyond Equation Search: Conjecture-Guided Discovery with SCOPE and ClosureBench](https://mlsanity.com/paper/2610.18938/) (2026)

## Abstract (arXiv)

Survey papers play a critical role in scientific communication by consolidating progress across a field. Recent advances in Large Language Models (LLMs) offer a promising solution by automating key steps in the survey-generation pipeline, such as retrieval, structuring, and summarization. However, existing LLM-based approaches often struggle with maintaining coherence across long, multi-section surveys and providing comprehensive citation coverage. To address these limitations, we introduce SurveyGen-I, an automatic survey generation framework that combines coarse-to-fine retrieval, adaptive planning, and memory-guided generation. SurveyGen-I first performs survey-level retrieval to construct the initial outline and writing plan, and then dynamically refines both during generation through a memory mechanism that stores previously written content and terminology, ensuring coherence across subsections. When the system detects insufficient context, it triggers fine-grained subsection-level retrieval. During generation, SurveyGen-I leverages this memory mechanism to maintain coherence across subsections. Experiments across four scientific domains demonstrate that SurveyGen-I consistently outperforms previous works in content quality, consistency, and citation coverage.