mlsanityData to 7 Oct 2026

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

arXiv 2603.08501 ↗First posted 9 Mar 2026cs.CLcited by 3

On the map: LLM agents and tool use → Web, search, and research agents

Abstract (arXiv)

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).

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use. Builds on 27 of its 51 references that are in the map. First posted on arXiv 9 Mar 2026.

Builds on

27 of 51 references.

Closest ancestors · 2

Same direction, newest first

  1. 2026From RAG to Agentic RAG for Faithful Islamic Question Answering12 Jan
  2. 2025Can LLMs Write Faithfully? An Agent-Based Evaluation of LLM-generated Islamic Content28 Oct

Other references · 25

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  2. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  3. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  4. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  5. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  6. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,800
  7. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,203
  8. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 940
  9. 2024WildChat: 1M ChatGPT Interaction Logs in the Wildcited by 598
  10. 2023LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Datasetcited by 449
  11. 2022MRKL Systems: A modular, neuro-symbolic architecture that combines large language models, external knowledge sources and discrete reasoningcited by 153
  12. 2025Fanar: An Arabic-Centric Multimodal Generative AI Platformcited by 67
13 more
  1. 2025SimpleQA Verified: A Reliable Factuality Benchmark to Measure Parametric Knowledgecited by 44
  2. 2024NativQA: Multilingual Culturally-Aligned Natural Query for LLMscited by 30
  3. 2025Large Language Models Meet Knowledge Graphs for Question Answering: Synthesis and Opportunitiescited by 30
  4. 2025A Survey of Multimodal Hallucination Evaluation and Detectioncited by 26
  5. 2025PalmX 2025: The First Shared Task on Benchmarking LLMs on Arabic and Islamic Culturecited by 20
  6. 2025AraHalluEval: A Fine-grained Hallucination Evaluation Framework for Arabic LLMscited by 12
  7. 2025Sacred or Synthetic? Evaluating LLM Reliability and Abstention for Religious Questionscited by 10
  8. 2024Improving LLM Reliability with RAG in Religious Question-Answering: MufassirQAScited by 6
  9. 2025Cross-Language Approach for Quranic QAcited by 5
  10. 2025MizanQA: Benchmarking Large Language Models on Moroccan Legal Question Answeringcited by 5
  11. 2025QU-NLP at QIAS 2025 Shared Task: A Two-Phase LLM Fine-Tuning and Retrieval-Augmented Generation Approach for Islamic Inheritance Reasoningcited by 4
  12. 2025QuranMorph: Morphologically Annotated Quranic Corpuscited by 1
  13. 2025FARSIQA: Faithful and Advanced RAG System for Islamic Question Answeringcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Islamic Large Language Models: From Knowledge Acquisition to Trustworthy and Hallucination-Resistant AIcited by 0
  2. 2026IslamicTurathBench: A Multi-Task, Multi-Discipline Benchmark for Evaluating Large Language Models on the Islamic Scholarly Tradition (turath)cited by 0
  3. 2026Hadith computational science in the age of large language models: a critical narrative reviewcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Ansari: A Retrieval-Grounded Islamic AI Assistant -- Architecture, Deployment, and Lessons from 140,000 Conversations
  2. 2026Muslim: A Deployed Arabic Voice AI Platform for Grounded Islamic Knowledge
  3. 2025Transformer Tafsir at QIAS 2025 Shared Task: Hybrid Retrieval-Augmented Generation for Islamic Knowledge Question Answering
  4. 2025Investigating Retrieval-Augmented Generation in Quranic Studies: A Study of 13 Open-Source Large Language Models
  5. 2025From RAG to Agentic: Validating Islamic-Medicine Responses with LLM Agents
  6. 2026What Makes a Good Fiqh Retriever? Answer Retrieval for Arabic Islamic Jurisprudence
  7. 2025Learning to Route: A Rule-Driven Agent Framework for Hybrid-Source Retrieval-Augmented Generation
  8. 2026KumbhDoot: A Scale-Ready, LLM-Bounded Architecture for Mass-Gathering Public-Service Assistants