arXiv 2509.189702025-11-18cs.AI

基于大语言模型（LLM）的智能体存在幻觉问题：分类、方法与方向综述

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

Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络安全学院）；Nanyang Technological University（南洋理工大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Hong Kong University of Science and Technology（香港科技大学）；School of Cyber Science and Engineering, Wuhan University（武汉大学网络安全科学与工程学院）；Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学中关村人工智能学院）；Academy of Mathematics and Systems Science, Chinese Academy of Sciences（中国科学院数学与系统科学研究院）；School of Computing, Faculty of Science and Engineering, Macquarie University（麦考瑞大学计算机学院）；Cyberspace Institute of Advanced Technology, Guangzhou University（广州大学高级技术网络研究所）；Squirrel Ai Learning；Xiaomi Company（小米公司）

Xixun Lin, Yucheng Ning, Jingwen Zhang, Yan Dong, Yilong Liu, Yongxuan Wu, Xiaohua Qi, Nan Sun, Yanmin Shang, Kun Wang, Pengfei Cao, Qingyue Wang, Lixin Zou, Xu… 展开作者

Xixun Lin, Yucheng Ning, Jingwen Zhang, Yan Dong, Yilong Liu, Yongxuan Wu, Xiaohua Qi, Nan Sun, Yanmin Shang, Kun Wang, Pengfei Cao, Qingyue Wang, Lixin Zou, Xu Chen, Chuan Zhou, Jia Wu, Peng Zhang, Qingsong Wen, Shirui Pan, Bin Wang, Yanan Cao, Kai Chen, Songlin Hu, Li Guo

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文首次全面综述基于LLM的智能体幻觉问题，通过分析智能体工作流程提出新分类法，研究18个触发原因，总结缓解与检测方法并指出未来方向，旨在推动更可靠的智能体系统发展。

摘要：

在大语言模型（LLMs）快速发展的推动下，基于LLM的智能体已成为具备类人认知、推理和交互能力的强大智能系统，正越来越多地应用于学生教育、科学研究和金融分析等各类现实场景。然而，尽管潜力显著，基于LLM的智能体仍易受幻觉问题影响，可能导致任务执行错误，削弱整体系统设计的可靠性。应对这一关键挑战需要深入理解并系统整合基于LLM的智能体的最新进展。为此，我们首次提出关于基于LLM的智能体幻觉问题的全面综述。通过仔细分析智能体的完整工作流程，我们提出一种新的分类法，识别出不同阶段出现的各类智能体幻觉。此外，我们深入研究了导致智能体幻觉出现的18个触发原因。通过详细回顾大量现有研究，我们总结了幻觉缓解与检测的方法，并指出未来研究的潜在方向。我们希望本综述能激发更多解决基于LLM的智能体幻觉问题的努力，最终推动更稳健、可靠的智能体系统的发展。

英文摘要：

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.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。