Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2508.14317 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908495505260544 |
|---|---|
| author | Chen, Jing Yang, Zhiheng Shen, Yixian Liu, Jie Belloum, Adam Papagainni, Chrysa Grosso, Paola |
| author_facet | Chen, Jing Yang, Zhiheng Shen, Yixian Liu, Jie Belloum, Adam Papagainni, Chrysa Grosso, Paola |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_14317 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SurveyGen-I: Consistent Scientific Survey Generation with Evolving Plans and Memory-Guided Writing Chen, Jing Yang, Zhiheng Shen, Yixian Liu, Jie Belloum, Adam Papagainni, Chrysa Grosso, Paola Computation and Language Information Retrieval 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. |
| title | SurveyGen-I: Consistent Scientific Survey Generation with Evolving Plans and Memory-Guided Writing |
| topic | Computation and Language Information Retrieval |
| url | https://arxiv.org/abs/2508.14317 |