aiqbench analysis
Fanar-Sadiq addresses critical limitations in religious LLMs by replacing standard RAG pipelines with a multi-agent architecture that ensures grounding in canonical texts and handles complex fiqh computations. The system's intent-aware routing and verification traces directly mitigate hallucination risks in high-stakes domains like zakat and inheritance calculations. With over 1.9 million accesses in its first year, this tool-augmented approach demonstrates strong practical viability for specialized verticals requiring deterministic reasoning.
Fanar-Sadiq: A Multi-Agent Architecture for Grounded Islamic QA
arXiv:2603.08501v3 Announce Type: replace Abstract: 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) improves grounding, however, a single retrieve-then-generate pipeline is insufficient for diverse Islamic queries, including verbatim scripture, citation-grounded guidance, and rule-constrained computations such as zakat and inheritance. To address these challenges, we present Fanar-Sadiq, a bilingual Arabic-English Islamic QA system built on a multi-agent, tool-augmented architecture. It is a core component of the Fanar AI platform. Fanar-Sadiq routes Islamic queries to specialized modules within an agentic tool architecture. It supports intent-aware routing, retrieval-grounded fiqh answers with normalized citations and verification traces, exact verse lookup with quotation validation, and deterministic Sunni zakat and inheritance calculators with madhhab-sensitive branching. We evaluate the end-to-end system on public Islamic QA benchmarks and show strong effectiveness and efficiency. It is publicly accessible through an API and Web application and has received over 1.9M accesses in less than a year (https://api.fanar.qa/docs).
Abstract: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) improves grounding, however, a single retrieve-then-generate pipeline is insufficient for diverse Islamic queries, including verbatim scripture, citation-grounded guidance, and rule-constrained computations such as zakat and inheritance. To address these challenges, we present Fanar-Sadiq, a bilingual Arabic-English Islamic QA system built on a multi-agent, tool-augmented architecture. It is a core component of the Fanar AI platform. Fanar-Sadiq routes Islamic queries to specialized modules within an agentic tool architecture. It supports intent-aware routing, retrieval-grounded fiqh answers with normalized citations and verification traces, exact verse lookup with quotation validation, and deterministic Sunni zakat and inheritance calculators with madhhab-sensitive branching. We evaluate the end-to-end system on public Islamic QA benchmarks and show strong effectiveness and efficiency. It is publicly accessible through an API and Web application and has received over 1.9M accesses in less than a year (this https URL).
Computation and Language (cs.CL)
arXiv:2603.08501 [cs.CL]
(or arXiv:2603.08501v3 [cs.CL] for this version)
Full text under the publisher's open licence · 189 words
Related coverage
Ansari: A Retrieval-Grounded Islamic AI Assistant -- Architecture, Deployment, and Lessons from 140,000 Conversations
arXiv · Aug 24, 2026
[AINews] Reality Checks on AI News (Yegge shuts down Gas Town, Databricks’ +60% Astra cost)
Latent Space · Sep 17, 2026
How Ninth Wave built AI-powered open finance onboarding on Amazon Bedrock
AWS · Sep 14, 2026
How Cohere Health digitizes clinical policies using Amazon Bedrock AgentCore
AWS · Aug 7, 2026