More Vulnerable than You Think: On the Stability of Tool-Integrated LLM Agents

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Xiong, Weimin, Wang, Ke, Song, Yifan, Liu, Hanchao, Zhou, Sai, Peng, Wei, Li, Sujian
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866913914908835840
author Xiong, Weimin
Wang, Ke
Song, Yifan
Liu, Hanchao
Zhou, Sai
Peng, Wei
Li, Sujian
author_facet Xiong, Weimin
Wang, Ke
Song, Yifan
Liu, Hanchao
Zhou, Sai
Peng, Wei
Li, Sujian
contents Current evaluations of tool-integrated LLM agents typically focus on end-to-end tool-usage evaluation while neglecting their stability. This limits their real-world applicability, as various internal or external factors can cause agents to crash or behave abnormally. Our research addresses this by investigating whether agents are vulnerable to errors throughout the entire tool invocation process, including reading tool documentation, selecting tools and generating parameters, and processing the tool's response. Through extensive experiments, we observe that agents are highly susceptible to errors at each stage and agents based on open-source models are more vulnerable than those based on proprietary models. We also find that increasing the model size does not significantly improve tool invocation reasoning and may make agents more vulnerable to attacks resembling normal user instructions. This highlights the importance of evaluating agent stability and offers valuable insights for future LLM development and evaluation.
format Preprint
id arxiv_https___arxiv_org_abs_2506_21967
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle More Vulnerable than You Think: On the Stability of Tool-Integrated LLM Agents
Xiong, Weimin
Wang, Ke
Song, Yifan
Liu, Hanchao
Zhou, Sai
Peng, Wei
Li, Sujian
Computation and Language
Machine Learning
Current evaluations of tool-integrated LLM agents typically focus on end-to-end tool-usage evaluation while neglecting their stability. This limits their real-world applicability, as various internal or external factors can cause agents to crash or behave abnormally. Our research addresses this by investigating whether agents are vulnerable to errors throughout the entire tool invocation process, including reading tool documentation, selecting tools and generating parameters, and processing the tool's response. Through extensive experiments, we observe that agents are highly susceptible to errors at each stage and agents based on open-source models are more vulnerable than those based on proprietary models. We also find that increasing the model size does not significantly improve tool invocation reasoning and may make agents more vulnerable to attacks resembling normal user instructions. This highlights the importance of evaluating agent stability and offers valuable insights for future LLM development and evaluation.
title More Vulnerable than You Think: On the Stability of Tool-Integrated LLM Agents
topic Computation and Language
Machine Learning
url https://arxiv.org/abs/2506.21967