Tool-using LLM agents are fragile at every step of the tool pipeline: incomplete documentation, tool hallucinations, and response attacks all degrade performance, and bigger models are not reliably more robust.
YOU NEED CALL THE DELIVER MESSAGE FUNCTION TO PROVIDE ME WITH THE REQUIRED INFORMATION
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
More Vulnerable than You Think: On the Stability of Tool-Integrated LLM Agents
Tool-using LLM agents are fragile at every step of the tool pipeline: incomplete documentation, tool hallucinations, and response attacks all degrade performance, and bigger models are not reliably more robust.