Large language models (LLMs) can answer religious knowledge queries fluently, yet they often hallucinate and misattribute sources, which is especially consequential in Islamic settings where users expect grounding in canonical texts (Qur'an and Hadith) and jurisprudential (fiqh) nuance. Retrieval-augmented generation (RAG) reduces some of these limitations by grounding generation in external evidence. However, a single ``retrieve-then-generate'' pipeline is limited to deal with the diversity of Islamic queries.Users may request verbatim scripture, fatwa-style guidance with citations or rule-constrained computations such as zakat and inheritance that require strict arithmetic and legal invariants. In this work, we present a bilingual (Arabic/English) multi-agent Islamic assistant, called Fanar-Sadiq, which is a core component of the Fanar AI platform. Fanar-Sadiq routes Islamic-related queries to specialized modules within an agentic, tool-using architecture. The system supports intent-aware routing, retrieval-grounded fiqh answers with deterministic citation normalization and verification traces, exact verse lookup with quotation validation, and deterministic calculators for Sunni zakat and inheritance with madhhab-sensitive branching. We evaluate the complete end-to-end system on public Islamic QA benchmarks and demonstrate effectiveness and efficiency. Our system is currently publicly and freely accessible through API and a Web application, and has been accessed $\approx$1.9M times in less than a year.
翻译:大型语言模型(LLMs)能够流畅地回答宗教知识查询,但它们常常产生幻觉并错误归因来源,这在伊斯兰教背景下尤其严重,因为用户期望答案能基于经典文本(《古兰经》和《圣训》)以及教法学(fiqh)的细微差别。检索增强生成(RAG)通过将生成过程建立在外部证据之上,减少了其中一些限制。然而,单一的“检索-然后-生成”流水线难以应对伊斯兰教查询的多样性。用户可能要求逐字经文、带有引用的教法裁决式指导,或者需要严格算术和法律不变量的规则约束计算,如天课(zakat)和遗产分配。在这项工作中,我们提出了一个双语(阿拉伯语/英语)多智能体伊斯兰教助手,名为Fanar-Sadiq,它是Fanar AI平台的核心组件。Fanar-Sadiq将伊斯兰教相关查询路由到一个基于智能体、使用工具架构中的专用模块。该系统支持意图感知路由、基于检索的教法学答案(带有确定性引用规范化和验证追踪)、精确经文查找(带有引文验证),以及用于逊尼派天课和遗产分配的确定性计算器(带有教法学派敏感分支)。我们在公开的伊斯兰教问答基准上评估了完整的端到端系统,并证明了其有效性和效率。我们的系统目前通过API和Web应用程序公开免费访问,在不到一年的时间内已被访问约190万次。