mlsanityData to 13 Oct 2026

Mitigating Hallucination in Large Language Models (LLMs): An Application-Oriented Survey on RAG, Reasoning, and Agentic Systems

arXiv 2510.24476 ↗First posted 28 Oct 2025cs.CL cs.AIcited by 2

On the map: LLM reasoning → Hallucination detection and mitigation

also in 1 more
Abstract (arXiv)

Hallucination remains one of the key obstacles to the reliable deployment of large language models (LLMs). Although various mitigation approaches have been proposed, existing studies often analyze different technical paradigms independently, lacking a unified perspective to understand the underlying mechanisms of different approaches and their correspondence with different types of hallucinations. This survey adopts a capability enhancement perspective to systematically examine hallucination mitigation approaches, focusing on Retrieval-Augmented Generation (RAG), reasoning enhancement, and their integration within agentic systems. Based on their primary mitigation mechanisms, we categorize hallucinations into knowledge-based hallucinations and logic-based hallucinations, analyze how RAG and reasoning enhancement methods respectively improve knowledge acquisition and reasoning reliability, and further discuss the integration mechanisms of retrieval and reasoning capabilities in Agentic Systems for mitigating composite hallucinations. By considering the applicability, mitigation mechanisms, and limitations of different approaches, this survey establishes a unified analytical framework connecting hallucination types, key capability dimensions, and technical paradigms.

Key facts. Cited by 2 papers in the map (data through 13 Oct 2026). Placed in Hallucination detection and mitigation, one of 17 directions in LLM reasoning. Builds on 26 of its 179 references that are in the map. First posted on arXiv 28 Oct 2025.

Builds on

26 of 179 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025Medical Hallucinations in Foundation Models and Their Impact on Healthcare26 Feb

Other references · 25

  1. 2023GPT-4 Technical Reportcited by 18,278
  2. 2023Mistral 7Bcited by 3,123
  3. 2023A Survey of Large Language Modelscited by 2,559
  4. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,736
  5. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,433
  6. 2023Gemini: A Family of Highly Capable Multimodal Modelscited by 848
  7. 2024DeepSeek-V3 Technical Reportcited by 777
  8. 2024Hallucination of Multimodal Large Language Models: A Surveycited by 384
  9. 2025DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environmentscited by 273
  10. 2023A Comprehensive Survey of AI-Generated Content (AIGC): A History of Generative AI from GAN to ChatGPTcited by 224
  11. 2022Internet-augmented language models through few-shot prompting for open-domain question answeringcited by 131
  12. 2025HalluLens: LLM Hallucination Benchmarkcited by 90
13 more
  1. 2025AdaCoT: Pareto-Optimal Adaptive Chain-of-Thought Triggering via Reinforcement Learningcited by 87
  2. 2025Rank-R1: Enhancing Reasoning in LLM-based Document Rerankers via Reinforcement Learningcited by 59
  3. 2025LLM-based Agents Suffer from Hallucinations: A Survey of Taxonomy, Methods, and Directionscited by 50
  4. 2024A Survey on Large Language Model Hallucination via a Creativity Perspectivecited by 38
  5. 2025MedHallu: A Comprehensive Benchmark for Detecting Medical Hallucinations in Large Language Modelscited by 33
  6. 2025NodeRAG: Structuring Graph-based RAG with Heterogeneous Nodescited by 26
  7. 2025MA-RAG: Multi-Agent Retrieval-Augmented Generation via Collaborative Chain-of-Thought Reasoningcited by 25
  8. 2023BatGPT: A Bidirectional Autoregessive Talker from Generative Pre-trained Transformercited by 23
  9. 2025Chain-of-Thought Matters: Improving Long-Context Language Models with Reasoning Path Supervisioncited by 21
  10. 2025InfoDeepSeek: Benchmarking Agentic Information Seeking for Retrieval-Augmented Generationcited by 15
  11. 2025LLM4Ranking: An Easy-to-use Framework of Utilizing Large Language Models for Document Rerankingcited by 12
  12. 2025L-MARS: Legal Multi-Agent System with Agentic Search and Citation-Faithfulness Auditcited by 11
  13. 2025Agent-UniRAG: A Trainable Open-Source LLM Agent Framework for Unified Retrieval-Augmented Generation Systemscited by 2

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026PRISM: Probing Reasoning, Instruction, and Source Memory in LLM Hallucinationscited by 4
  2. 2026RAGent: Physics-Aware Agentic Reasoning for Training-Free mmWave Human Activity Recognitioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025From "Hallucination" to "Suture": Insights from Language Philosophy to Enhance Large Language Models
  2. 2025InEx: Hallucination Mitigation via Introspection and Cross-Modal Multi-Agent Collaboration
  3. 2026Mitigating Prompt-Induced Hallucinations in Large Language Models via Structured Reasoning
  4. 2025HEAL: An Empirical Study on Hallucinations in Embodied Agents Driven by Large Language Models
  5. 2025Auditing Meta-Cognitive Hallucinations in Reasoning Large Language Models
  6. 2026Hallucination Cascade: Analyzing Error Propagation in Multi-Agent LLM Systems
  7. 2025QueryBandits for Hallucination Mitigation: Exploiting Semantic Features for No-Regret Rewriting
  8. 2026HalluWorld: A Controlled Benchmark for Hallucination via Reference World Models