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

TL;DR

SurveyGen-I is an automated framework that enhances scientific survey generation by integrating retrieval, adaptive planning, and memory-guided writing to improve coherence and citation coverage across multi-section surveys.

Contribution

It introduces a novel memory-guided, adaptive planning approach for LLM-based survey generation, addressing coherence and coverage limitations of prior methods.

Findings

Outperforms previous methods in content quality

Achieves higher coherence across survey sections

Provides more comprehensive citation coverage

Abstract

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.