IRCLOct 17, 2025

SQuAI: Scientific Question-Answering with Multi-Agent Retrieval-Augmented Generation

arXiv:2510.15682v13 citationsh-index: 3CIKM
Originality Incremental advance
AI Analysis

It addresses the need for accurate, verifiable answers to complex scientific questions, though it is incremental as it builds on existing RAG methods.

The paper tackles the problem of scientific question answering by developing SQuAI, a multi-agent retrieval-augmented generation framework that improves faithfulness, answer relevance, and contextual relevance by up to 12% over a baseline.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes