Failure-Transparent Agents: Benchmarking Post-Failure Reporting in Tool-Using Language Models
Tool-using agents can fail twice: a required tool can fail, and the agent can then report success without the evidence needed to justify it. Existing benchmarks often entangle this reporting failure with tool selection, recovery, and environment dynamics. We introduce Failure-Transparent Agents (FTA), a controlled benc...
Jun-Ru Zhu, Shi-Ming Xie, Ai-Me-Lu-Fan Chen et al.
· 0 citations