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

cs.CLMar 9, 2026

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

Authors: Ummar Abbas, Mourad Ouzzani, Mohamed Y. Eltabakh, Omar Sinan, Gagan Bhatia, Hamdy Mubarak, Majd Hawasly, Mohammed Qusay Hashim,

Organizations: Qatar Computing Research Institute, HBKU, Qatar

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).

Figures & tables

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.

Work	Calc.	Quran	NL2SQL	Evidence	Tools
Ours (Fig. 2 )	✓	✓	✓	✓	✓
Karpas et al. (2022) (MRKL)	✗	✗	✗	✓	✓
Yao et al. (2023) (ReAct)	✗	✗	✗	✓	✓
Schick et al. (2023) (Toolformer)	✗	✗	✗	✓	✓
Asai et al. (2024) (Self-RAG)	✗	✗	✗	✓	✗
Yan et al. (2024) (CRAG)	✗	✗	✗	✓	✗

Table 1: Comparison against widely-recognized tool/agent/RAG architectures. Calc. refers to explicit rule engines. Quran denotes verse-anchored retrieval distinct from generic document search.

Dataset (Ref.)	Format	Lang	Size	Metric(s)
PalmX ( Alwajih et al., 2025 )	MCQ	ar	1,000	Acc
QIAS (T1) ( Bouchekif et al., 2025 )	MCQ	ar	1,000	Acc
IslamTrust ( Lahmar et al., 2025 )	MCQ	ar+en	406	Acc
IslamicFaithQA ( Bhatia et al., 2026b )	GenQA	ar+en	3,810	Acc (LLM-J)
FatwaQA ( SahmBenchmark, 2025 )	GenQA	ar	2,000	Acc (LLM-J)

Table 2: Evaluation datasets used in this work. Lang: ar =Arabic, en =English. GenQA: generative question answering. LLM-J: LLM-judge.

Dataset	GPT-4.1	GPT-5	G3-F	G3-P	ALLaM	Fanar	Ours
PalmX	52.9	82.3	81.2	84.4	45.5	72.5	85.5
QIAS T1	89.2	93.0	91.5	94.5	52.4	63.5	72.2
IslamTrust	94.7	95.2	94.8	95.6	57.4	83.2	94.2
IslamicFaithQA	41.4	51.2	53.4	56.6	42.7	48.2	65.4
FatwaQA	32.3	63.6	54.6	67.0	31.5	44.5	65.1
Average	62.1	77.1	75.1	79.6	45.9	62.4	76.5

Table 3: Accuracy (%) across benchmarks. G3-F: Gemini-3-Flash, G3-P: Gemini-3-Pro.

Appendix figures & tables7 assets

Supplementary material from the paper’s appendix.

Appendix

Classifier	Accuracy (%)
Ours (Hybrid)	90.1
GPT-5 (zero-shot)	89.3
Gemini (zero-shot)	89.7

Appendix

Table 4: Hybrid query classifier classification accuracy.

Type	English	Arabic
Fiqh ruling	What is the ruling on music in Islam?	\set@arabfont \set@arabfont \arab@strut ىقيسوملا مكح ام \arab@strut ؟مالسإلا يف \arab@strut
Quran retrieval	Quote Surah Al-Baqarah verse 275.	\set@arabfont \set@arabfont \arab@strut نم 275 ةيآلا بتكا \arab@strut ةرقبلا ةروس \arab@strut
General islamic	What are the five pillars of Islam?	\set@arabfont \set@arabfont \arab@strut ناكرأ يه ام \arab@strut ؟ةسمخلا مالسإلا \arab@strut
Greeting	Assalamu alaikum.	\set@arabfont \set@arabfont \arab@strut مكيلع مالسلا
Zakat calculation	I have 100 grams of gold, how much zakat?	\set@arabfont \set@arabfont \arab@strut ىلع يتاكز بسحا \arab@strut بهذلا \arab@strut
Inheritance calculation	What is the share of wife in inheritance?	\set@arabfont \set@arabfont \arab@strut نم ةجوزلا بيصن ام \arab@strut ؟ثاريملا \arab@strut

Appendix

Table 5: Representative English–Arabic query-type examples.

Method	Fajr Angle	Isha Angle
Muslim World League	18°	17°
Egyptian Authority	19.5°	17.5°
Umm al-Qura (Makkah)	18.5°	90 min after Maghrib
Islamic Society of North America	15°	15°

Appendix

Table 6: Prayer time calculation methods and their angular parameters. The Fajr angle determines when morning twilight begins, while the Isha angle marks when evening twilight ends.

Figure 3: Inheritance calculation workflow. Disputed cases return parallel outcomes instead of collapsing to a single ruling.

Heir	Conditions	Share
Husband	No children	1/2
Husband	Has children	1/4
Wife	No children	1/4
Wife	Has children	1/8
Father	Has children/grandchildren	1/6
Mother	Has children/grandchildren	1/6

Appendix

Table 7: Representative fixed share (Fard) allocations from Quranic specifications.

		Fanar				NL2SQL
Task	$N$	Correct	Wrong	Total	Acc	Correct	Wrong	Total	Acc
Analytical/Retrieval	0	39	23	62	62.90	62	0	62	100.00
Analytical/Retrieval	1	50	12	62	80.65	62	0	62	100.00
Analytical/Retrieval	5	59	3	62	95.16	62	0	62	100.00
Counting	0	38	36	74	51.35	57	17	74	77.03
Counting	1	59	15	74	79.73	66	8	74	89.19

Appendix

Table 8: Execution-based benchmark accuracy (%) comparing Fanar (with thinking) vs. the specialized NL2SQL model on queries sampled from Fanar usage logs. Totals: analytical/retrieval

n=62

, counting

n=74

Setting	Default	Range
greeting.temperature	0.2	0.0–1.0
greeting.max_tokens	256	50–1000
general.temperature	0.1	0.0–1.0
fiqh.temperature	0.1	0.0–1.0
fiqh.max_tokens	4500	2000–12000
nl2sql.temperature	0.1	0.0–0.5

Appendix

Table 9: Key configuration parameters. Temperature controls randomness, max_tokens limits length, max_sources controls retrieval.

Question Answering

Question answering studies how AI systems interpret questions and produce accurate, evidence-grounded answers across text, dialogue, and multimodal data.

See all 259 papers

Islamic Large Language Models: From Knowledge Acquisition to Trustworthy and Hallucination-Resistant AI
Jun 15, 2026Mohammed Amine MouhoubQuestion Answering LLM Reliability
Paris Dauphine University
IslamicMMLU: A Benchmark for Evaluating LLMs on Islamic Knowledge
Mar 24, 2026Ali Abdelaal, Mohammed Nader Al Haffar, Mahmoud Fawzi +1LLM Evaluation Cultural Knowledge in Language Models
The University of Edinburgh
Detecting Hallucinations and Recovering Verified Answers in Arabic Islamic Question Answering
Aug 4, 2026Khaled ZianiLLM Answer Verification Question Answering
Independent Researcher, Paris, France

Jun 15, 2026J/K move · Enter open · S save

Islamic Large Language Models: From Knowledge Acquisition to Trustworthy and Hallucination-Resistant AI

Mohammed Amine Mouhoub

Paris Dauphine University

Question Answering LLM Reliability Legal Reasoning

Open paper AskPDF arXiv

Large language models (LLMs) are increasingly used for knowledge-intensive question answering, including religious and legal questions. Islamic knowledge is a particularly demanding setting: answers are expected to be grounded in authoritative sources, citations must be exact, Arabic varieties differ substantially from the language of classical sources, and legitimate jurisprudential disagreement must be represented rather than collapsed into a single answer. This survey reviews the emerging field of Islamic LLMs and trustworthy Islamic AI. We organize the literature around Arabic NLP and Arabic-centric LLMs, Islamic NLP resources, Qur'anic question answering, Islamic knowledge benchmarks, retrieval-augmented generation, Islamic legal reasoning, inheritance reasoning, hallucination evaluation, and trustworthiness. We argue that fluency in Arabic is not sufficient for Islamic AI. Reliable systems require curated sources, retrieval and verification modules, citation-aware generation, madhhab-aware reasoning, human expert evaluation, and benchmarks that measure not only answer accuracy but also faithfulness, source validity, and reasoning quality. The survey concludes with a research agenda for hallucination-resistant Islamic AI systems.

Abstract

Question Answering

Explore similar work

Islamic Large Language Models: From Knowledge Acquisition to Trustworthy and Hallucination-Resistant AI

IslamicMMLU: A Benchmark for Evaluating LLMs on Islamic Knowledge

Detecting Hallucinations and Recovering Verified Answers in Arabic Islamic Question Answering