用多智能体增强检索生成，让大模型回答科学问题更准确可信。
SQuAI: Scientific Question-Answering with Multi-Agent Retrieval-Augmented Generation
- 四智能体协作拆解问题、混合检索文献并动态过滤相关文档。
- 在1000个科学问题上，答案忠实度和相关性提升最高达12%。
- 支持可追溯引用与透明推理，适合科研人员与学术验证场景。
我们提出SQuAI（https://squai.scads.ai/），一个面向科学问答的可扩展、可信多智能体检索增强生成框架。该系统基于arXiv.org超过230万篇全文论文，通过四个协同智能体将复杂问题分解为子问题，采用混合稀疏-稠密检索方法精准获取证据，并自适应过滤文档以提升上下文相关性。为确保答案忠实与可追溯，SQuAI对每个主张添加内联引用，并提供原文支持句。实验显示，相比强基线，其在忠实度、答案相关性和上下文相关性上最高提升0.088（12%）。研究还发布了包含1000个科学问题-答案-证据三元组的基准数据集，以支持可复现性。SQuAI展示了多智能体RAG如何实现更可信的科学领域大模型问答。
原文摘要 · Abstract (English)
We present SQuAI (https://squai.scads.ai/), a scalable and trustworthy multi-agent retrieval-augmented generation (RAG) framework for scientific question answering (QA) with large language models (LLMs). SQuAI addresses key limitations of existing RAG systems in the scholarly domain, where complex, open-domain questions demand accurate answers, explicit claims with citations, and retrieval across millions of scientific documents. Built on over 2.3 million full-text papers from arXiv.org, SQuAI employs four collaborative agents to decompose complex questions into sub-questions, retrieve targeted evidence via hybrid sparse-dense retrieval, and adaptively filter documents to improve contextual relevance. To ensure faithfulness and traceability, SQuAI integrates in-line citations for each generated claim and provides supporting sentences from the source documents. Our system improves faithfulness, answer relevance, and contextual relevance by up to +0.088 (12%) over a strong RAG baseline. We further release a benchmark of 1,000 scientific question-answer-evidence triplets to support reproducibility. With transparent reasoning, verifiable citations, and domain-wide scalability, SQuAI demonstrates how multi-agent RAG enables more trustworthy scientific QA with LLMs.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。