Preprint
Oct 2026
SSCBench: Evaluating the Evidential Validity of Fault-Injection Tests for Tool-Using LLM Agents
Fault injection is increasingly used to evaluate the reliability of tool-using LLM agents. However, there has been limited study of how fault-adoption results should be interpreted when the agent itself determines which authoritative observations become visible during execution. In this paper, we present a systematic s...
Xin-Cheng He, Wan-Li Dong, Zhao-Qiang Guo et al.
· 0 citations