SQuAI：基于多智能体检索增强生成的科学问答
SQuAI: Scientific Question-Answering with Multi-Agent Retrieval-Augmented Generation
AI总结：
SQuAI是一个多智能体检索增强生成框架，通过分解问题、混合检索和自适应过滤，在230万篇论文上提升科学问答的忠实性和相关性，并发布千级基准。
摘要：
我们提出了SQuAI（https://squai.scads.ai/），一个可扩展且可信赖的多智能体检索增强生成（RAG）框架，用于基于大语言模型（LLM）的科学问答（QA）。SQuAI解决了现有RAG系统在学术领域的关键局限性，在该领域中，复杂的开放域问题需要准确的答案、带有引用的明确声明以及跨数百万篇科学文档的检索。SQuAI基于arXiv.org上超过230万篇全文论文构建，采用四个协作智能体将复杂问题分解为子问题，通过混合稀疏-稠密检索获取针对性证据，并自适应过滤文档以提高上下文相关性。为确保忠实性和可追溯性，SQuAI为每个生成的声明集成了行内引用，并提供来自源文档的支持句。我们的系统在忠实性、答案相关性和上下文相关性方面相较于强RAG基线提升了高达+0.088（12%）。我们进一步发布了一个包含1,000个科学问题-答案-证据三元组的基准测试，以支持可复现性。凭借透明的推理、可验证的引用和领域范围的扩展性，SQuAI展示了多智能体RAG如何实现更可信赖的基于LLM的科学问答。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
