SciSage: A Multi-Agent Framework for High-Quality Scientific Survey Generation

TL;DR

SciSage is a multi-agent framework that enhances scientific survey generation by improving structural coherence, citation reliability, and topical breadth through hierarchical evaluation and specialized agents, outperforming existing methods in key metrics.

Contribution

Introduces SciSage, a novel multi-agent system employing hierarchical critique and collaboration for high-quality automated scientific survey generation.

Findings

Outperforms state-of-the-art baselines in coherence and citation metrics.

Achieves +1.73 points in document coherence and +32% in citation F1 scores.

Human evaluations show mixed results but highlight strengths in topical breadth and retrieval.

Abstract

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.