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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lin, Xixun, Ning, Yucheng, Zhang, Jingwen, Dong, Yan, Liu, Yilong, Wu, Yongxuan, Qi, Xiaohua, Sun, Nan, Shang, Yanmin, Wang, Kun, Cao, Pengfei, Wang, Qingyue, Zou, Lixin, Chen, Xu, Zhou, Chuan, Wu, Jia, Zhang, Peng, Wen, Qingsong, Pan, Shirui, Wang, Bin, Cao, Yanan, Chen, Kai, Hu, Songlin, Guo, Li
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911272996438016
author Lin, Xixun
Ning, Yucheng
Zhang, Jingwen
Dong, Yan
Liu, Yilong
Wu, Yongxuan
Qi, Xiaohua
Sun, Nan
Shang, Yanmin
Wang, Kun
Cao, Pengfei
Wang, Qingyue
Zou, Lixin
Chen, Xu
Zhou, Chuan
Wu, Jia
Zhang, Peng
Wen, Qingsong
Pan, Shirui
Wang, Bin
Cao, Yanan
Chen, Kai
Hu, Songlin
Guo, Li
author_facet Lin, Xixun
Ning, Yucheng
Zhang, Jingwen
Dong, Yan
Liu, Yilong
Wu, Yongxuan
Qi, Xiaohua
Sun, Nan
Shang, Yanmin
Wang, Kun
Cao, Pengfei
Wang, Qingyue
Zou, Lixin
Chen, Xu
Zhou, Chuan
Wu, Jia
Zhang, Peng
Wen, Qingsong
Pan, Shirui
Wang, Bin
Cao, Yanan
Chen, Kai
Hu, Songlin
Guo, Li
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2509_18970
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LLM-based Agents Suffer from Hallucinations: A Survey of Taxonomy, Methods, and Directions
Lin, Xixun
Ning, Yucheng
Zhang, Jingwen
Dong, Yan
Liu, Yilong
Wu, Yongxuan
Qi, Xiaohua
Sun, Nan
Shang, Yanmin
Wang, Kun
Cao, Pengfei
Wang, Qingyue
Zou, Lixin
Chen, Xu
Zhou, Chuan
Wu, Jia
Zhang, Peng
Wen, Qingsong
Pan, Shirui
Wang, Bin
Cao, Yanan
Chen, Kai
Hu, Songlin
Guo, Li
Artificial Intelligence
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.
title LLM-based Agents Suffer from Hallucinations: A Survey of Taxonomy, Methods, and Directions
topic Artificial Intelligence
url https://arxiv.org/abs/2509.18970