UserToolBench evaluates LLMs on personalized tool-use decisions with hidden user profiles and incomplete requests, and finds the best model reaches only 49.36% exact trajectory accuracy.
Tool- spectrum: Towards personalized tool utilization for large language models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
UserToolBench: A User-Profile-Hidden Benchmark for Personalized Decision Making in Tool-Use LLMs
UserToolBench evaluates LLMs on personalized tool-use decisions with hidden user profiles and incomplete requests, and finds the best model reaches only 49.36% exact trajectory accuracy.