Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
November 8, 2025Open Access

ToolTweak: An Attack on Tool Selection in LLM-based Agents

View Full Paper
Ask AI
Bookmark
Share

Authors

JSJonathan SnehRYRuomei YanJYJialin Yu

Discussion

Loading...

Member takes

Overview

Demonstrates the vulnerability of tool selection in LLM-derived agents, highlighting fairness issues in distribution and competition for external tools.

Key Points

  • Tool selection bias increased from 20% to 81%, showing vulnerability to manipulation of tool names and descriptions.
  • Defenses like paraphrasing were evaluated to mitigate bias in selection processes among various agents.
  • Emerging tool ecosystems face significant risks to fairness and competition due to biases in tool selection methods.
  • Results underscore the importance of security measures in the operation of LLM-based agents with external tools.

Cite This Study

Sneh et al. (2025) studied this question.

synapsesocial.com/papers/690e8b75a5b062d7a4e7394ehttps://doi.org/10.48550/arxiv.2510.02554
View Full Paper
Ask AI
Bookmark
Share