Preprint
Aug 2026
ToolRobustBench: Stage-Wise Perturbation Evaluation and Failure Diagnosis for Tool-Calling Agents
ToolRobustBench provides a deterministic and cascade-aware benchmark for diagnosing robustness beyond clean tool-calling accuracy, where a tool-calling agent is an LLM system that selects a tool, supplies structured arguments, and interprets its returned feedback.
YiShan Zheng, Yuan Wu, Yi Chang
· 0 citations