LLM-based Agents Suffer from Hallucinations: A Survey of Taxonomy, Methods, and Directions

2025-09-23

AI Summary

Large language model (LLM)-based agents frequently suffer from hallucination—generating factually incorrect, inconsistent, or unsubstantiated content during cognition, reasoning, and interaction—severely compromising task reliability. Method: This work introduces the first holistic hallucination taxonomy spanning the agent’s entire lifecycle, identifying multi-stage hallucination types and systematically categorizing eighteen underlying causal mechanisms. Through process analysis, systematic literature review, and attribution modeling, we synthesize over one hundred existing studies to distill prevailing detection and mitigation strategies. Contribution/Results: The study establishes a unified theoretical framework for hallucination research, clarifying critical directions—including enhanced interpretability, multi-source verification, and dynamic feedback integration—that collectively advance the development of robust, trustworthy LLM-based agent systems.

Technology Category

• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Multiagent Systems: Other Foundations of Multi Agent Systems
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Agentic search

Abstract

Driven by the rapid advancements of Large Language Models (LLMs), LLM-based agents have emerged as powerful intelligent systems capable of human-like cognition, reasoning, and interaction. These agents are increasingly being deployed across diverse real-world applications, including student education, scientific research, and financial analysis. However, despite their remarkable potential, LLM-based agents remain vulnerable to hallucination issues, which can result in erroneous task execution and undermine the reliability of the overall system design. Addressing this critical challenge requires a deep understanding and a systematic consolidation of recent advances on LLM-based agents. To this end, we present the first comprehensive survey of hallucinations in LLM-based agents. By carefully analyzing the complete workflow of agents, we propose a new taxonomy that identifies different types of agent hallucinations occurring at different stages. Furthermore, we conduct an in-depth examination of eighteen triggering causes underlying the emergence of agent hallucinations. Through a detailed review of a large number of existing studies, we summarize approaches for hallucination mitigation and detection, and highlight promising directions for future research. We hope this survey will inspire further efforts toward addressing hallucinations in LLM-based agents, ultimately contributing to the development of more robust and reliable agent systems.

Problem

• Surveying hallucinations in LLM-based agents across different workflow stages
• Analyzing eighteen triggering causes for agent hallucination emergence
• Summarizing mitigation approaches and future research directions

Innovation

• Surveyed hallucination taxonomy across agent workflow stages
• Analyzed eighteen triggering causes for agent hallucinations
• Summarized mitigation and detection methods from existing studies