SciRAG: Adaptive, Citation-Aware, and Outline-Guided Retrieval and Synthesis for Scientific Literature

TL;DR

SciRAG is a novel framework that enhances scientific literature synthesis by integrating adaptive retrieval, citation-aware reasoning, and outline-guided synthesis, leading to more accurate and trustworthy scientific knowledge aggregation.

Contribution

The paper introduces SciRAG, a comprehensive system combining adaptive retrieval, citation graph reasoning, and outline-guided synthesis for improved scientific literature exploration.

Findings

Outperforms prior systems in factual accuracy

Achieves higher synthesis quality on benchmarks

Establishes a new foundation for scientific knowledge aggregation

Abstract

The accelerating growth of scientific publications has intensified the need for scalable, trustworthy systems to synthesize knowledge across diverse literature. While recent retrieval-augmented generation (RAG) methods have improved access to scientific information, they often overlook citation graph structure, adapt poorly to complex queries, and yield fragmented, hard-to-verify syntheses. We introduce SciRAG, an open-source framework for scientific literature exploration that addresses these gaps through three key innovations: (1) adaptive retrieval that flexibly alternates between sequential and parallel evidence gathering; (2) citation-aware symbolic reasoning that leverages citation graphs to organize and filter supporting documents; and (3) outline-guided synthesis that plans, critiques, and refines answers to ensure coherence and transparent attribution. Extensive experiments across multiple benchmarks such as QASA and ScholarQA demonstrate that SciRAG outperforms prior systems in factual accuracy and synthesis quality, establishing a new foundation for reliable, large-scale scientific knowledge aggregation.