范尔-萨迪克：面向伊斯兰教问答系统的多智能体基础架构

摘要

大型语言模型（LLMs）能够流畅回答宗教知识查询，但经常产生虚构内容并错误归因来源，这在伊斯兰应用场景中尤其严重——用户期望回答必须基于《古兰经》和圣训等经典文本，并体现教法学的细微差别。检索增强生成（RAG）技术通过将生成过程锚定于外部证据，部分缓解了这些局限。然而，单一的"检索-生成"流水线难以应对伊斯兰查询的多样性：用户可能要求直接引用经文、需要附有出处的教法裁决式指导，或是涉及天课与继承等需严格遵循算术规则和法律不变量的计算类问题。本研究提出双语言（阿拉伯语/英语）多智能体伊斯兰助手Fanar-Sadiq，作为Fanar AI平台的核心组件。该系统采用工具调用型智能体架构，将伊斯兰相关查询路由至专用模块，支持意图感知路由、带有确定性引文规范化与验证轨迹的检索锚定式教法回答、精确经文查找与引文验证，以及涵盖逊尼派天课与继承计算的可按教法学派分支的确定性计算器。我们在公开伊斯兰问答基准上对端到端系统进行评估，证明了其有效性与高效性。目前该系统通过API和网页应用向公众免费开放，在不到一年内已获得约190万次访问。

English

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 approx1.9M times in less than a year.

范尔-萨迪克：面向伊斯兰教问答系统的多智能体基础架构

Fanar-Sadiq: A Multi-Agent Architecture for Grounded Islamic QA

摘要

Support