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

arXiv: https://arxiv.org/abs/2511.14362 · HTML: https://mlsanity.com/paper/2511.14362/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 26 references that are in the map.
- First posted on arXiv 18 Nov 2025.

## Builds on (most cited first, 15 of 15)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [SciBERT: A Pretrained Language Model for Scientific Text](https://mlsanity.com/paper/1903.10676/) (2019)
- [PubMedQA: A Dataset for Biomedical Research Question Answering](https://mlsanity.com/paper/1909.06146/) (2019)
- [Fact or Fiction: Verifying Scientific Claims](https://mlsanity.com/paper/2004.14974/) (2020)
- [Prometheus 2: An Open Source Language Model Specialized in Evaluating Other Language Models](https://mlsanity.com/paper/2405.01535/) (2024)
- [MLAgentBench: Evaluating Language Agents on Machine Learning Experimentation](https://mlsanity.com/paper/2310.03302/) (2023)
- [SciCode: A Research Coding Benchmark Curated by Scientists](https://mlsanity.com/paper/2407.13168/) (2024)
- [Language agents achieve superhuman synthesis of scientific knowledge](https://mlsanity.com/paper/2409.13740/) (2024)
- [Large Language Models for Automated Open-domain Scientific Hypotheses Discovery](https://mlsanity.com/paper/2309.02726/) (2023)
- [OpenScholar: Synthesizing Scientific Literature with Retrieval-augmented LMs](https://mlsanity.com/paper/2411.14199/) (2024)
- [Growth rates of modern science: A bibliometric analysis based on the number of publications and cited references](https://mlsanity.com/paper/1402.4578/) (2014)
- [LitLLM: A Toolkit for Scientific Literature Review](https://mlsanity.com/paper/2402.01788/) (2024)
- [OpenResearcher: Unleashing AI for Accelerated Scientific Research](https://mlsanity.com/paper/2408.06941/) (2024)
- [SciDQA: A Deep Reading Comprehension Dataset over Scientific Papers](https://mlsanity.com/paper/2411.05338/) (2024)
- [LitFM: A Retrieval Augmented Structure-aware Foundation Model For Citation Graphs](https://mlsanity.com/paper/2409.12177/) (2024)

## Built on by (most cited first, 4 of 4)

- [Large Knowledge Model: From Papers to a Scientific Reasoning Landscape](https://mlsanity.com/paper/2609.27297/) (2026)
- [EMBL AI Librarian: Life-Sciences Knowledge Layer for AI Agents](https://mlsanity.com/paper/2607.28229/) (2026)
- [FootprintRAG: Visual Analytics for Evidence Context Refinement in RAG-based Scientific Literature Exploration](https://mlsanity.com/paper/2609.19601/) (2026)
- [PathAnchor: Path-Structured Evidence for Scientific Agents](https://mlsanity.com/paper/2609.38766/) (2026)

## Abstract (arXiv)

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.