Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Ummar Abbas, Mourad Ouzzani, Mohamed Y. Eltabakh, Omar Sinan, Gagan Bhatia, Hamdy Mubarak, Majd Hawasly, Mohammed Qusay Hashim, Kareem Darwish, Firoj Alam

TL;DR

This work presents a bilingual (Arabic/English) multi-agent Islamic assistant, called Fanar-Sadiq, which is a core component of the Fanar AI platform and evaluates the complete end-to-end system on public Islamic QA benchmarks and demonstrates effectiveness and efficiency.

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) 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.

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

TL;DR

This work presents a bilingual (Arabic/English) multi-agent Islamic assistant, called Fanar-Sadiq, which is a core component of the Fanar AI platform and evaluates the complete end-to-end system on public Islamic QA benchmarks and demonstrates effectiveness and efficiency.

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) 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 1.9M times in less than a year.
Paper Structure (40 sections, 3 equations, 3 figures, 8 tables, 2 algorithms)

This paper contains 40 sections, 3 equations, 3 figures, 8 tables, 2 algorithms.

Table of Contents

  1. Introduction
  2. Related Work
  3. Multi-Agent Tool-Using QA Systems
  4. Islamic RAG Assistants
  5. System Architecture
  6. Hybrid Query Classifier
  7. Primary (LLM) classifier.
  8. Fallback (prototype) classifier.
  9. Evaluation of the Hybrid Query Classifier
  10. Tool Calls
  11. Greeting Tool
  12. Islamic Calendar Tool
  13. Prayer Times and Qibla Tool
  14. Dua Lookup Tool
  15. Calculation Pipeline (Deterministic)
  16. ...and 25 more sections

Figures (3)

  • Figure 1: Illustrative end-to-end examples showing intent routing to specialized tools, traceable citations for fiqh QA, exact Quranic verse handling, deterministic zakat computation, and explicit madhhab-sensitive branching for disputed inheritance cases. Citation tags [C*] denote normalized evidence spans: [Q*] denotes verse-level citations.
  • Figure 2: Our multi-agent architecture. A hybrid query classifier selects among (i) tool calls, (ii) deterministic calculation, (iii) document-grounded retrieval QA, and (iv) Quranic retrieval routes, before assembling the final response with references.
  • Figure 3: Inheritance calculation workflow. Disputed cases return parallel outcomes instead of collapsing to a single ruling.