SciSage: A Multi-Agent Framework for High-Quality Scientific Survey Generation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915400132853760 |
|---|---|
| author | Shi, Xiaofeng Kou, Qian Li, Yuduo Tang, Ning Xie, Jinxin Yu, Longbin Wang, Songjing Zhou, Hua |
| author_facet | Shi, Xiaofeng Kou, Qian Li, Yuduo Tang, Ning Xie, Jinxin Yu, Longbin Wang, Songjing Zhou, Hua |
| contents | The rapid growth of scientific literature demands robust tools for automated survey-generation. However, current large language model (LLM)-based methods often lack in-depth analysis, structural coherence, and reliable citations. To address these limitations, we introduce SciSage, a multi-agent framework employing a reflect-when-you-write paradigm. SciSage features a hierarchical Reflector agent that critically evaluates drafts at outline, section, and document levels, collaborating with specialized agents for query interpretation, content retrieval, and refinement. We also release SurveyScope, a rigorously curated benchmark of 46 high-impact papers (2020-2025) across 11 computer science domains, with strict recency and citation-based quality controls. Evaluations demonstrate that SciSage outperforms state-of-the-art baselines (LLM x MapReduce-V2, AutoSurvey), achieving +1.73 points in document coherence and +32% in citation F1 scores. Human evaluations reveal mixed outcomes (3 wins vs. 7 losses against human-written surveys), but highlight SciSage's strengths in topical breadth and retrieval efficiency. Overall, SciSage offers a promising foundation for research-assistive writing tools. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_12689 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SciSage: A Multi-Agent Framework for High-Quality Scientific Survey Generation Shi, Xiaofeng Kou, Qian Li, Yuduo Tang, Ning Xie, Jinxin Yu, Longbin Wang, Songjing Zhou, Hua Artificial Intelligence Information Retrieval The rapid growth of scientific literature demands robust tools for automated survey-generation. However, current large language model (LLM)-based methods often lack in-depth analysis, structural coherence, and reliable citations. To address these limitations, we introduce SciSage, a multi-agent framework employing a reflect-when-you-write paradigm. SciSage features a hierarchical Reflector agent that critically evaluates drafts at outline, section, and document levels, collaborating with specialized agents for query interpretation, content retrieval, and refinement. We also release SurveyScope, a rigorously curated benchmark of 46 high-impact papers (2020-2025) across 11 computer science domains, with strict recency and citation-based quality controls. Evaluations demonstrate that SciSage outperforms state-of-the-art baselines (LLM x MapReduce-V2, AutoSurvey), achieving +1.73 points in document coherence and +32% in citation F1 scores. Human evaluations reveal mixed outcomes (3 wins vs. 7 losses against human-written surveys), but highlight SciSage's strengths in topical breadth and retrieval efficiency. Overall, SciSage offers a promising foundation for research-assistive writing tools. |
| title | SciSage: A Multi-Agent Framework for High-Quality Scientific Survey Generation |
| topic | Artificial Intelligence Information Retrieval |
| url | https://arxiv.org/abs/2506.12689 |