{"ID":2854124,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.15682","arxiv_id":"2510.15682","title":"SQuAI: Scientific Question-Answering with Multi-Agent Retrieval-Augmented Generation","abstract":"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.","short_abstract":"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 question...","url_abs":"https://arxiv.org/abs/2510.15682","url_pdf":"https://arxiv.org/pdf/2510.15682v1","authors":"[\"Ines Besrour\",\"Jingbo He\",\"Tobias Schreieder\",\"Michael Färber\"]","published":"2025-10-17T14:20:55Z","proceeding":"cs.IR","tasks":"[\"cs.IR\",\"cs.CL\"]","methods":"[\"RAG\",\"Large Language Model\",\"Language Model\"]","project_urls":"[\"https://squai.scads.ai/\"]","has_code":false}