ToolMisuseBench: An Offline Deterministic Benchmark for Tool Misuse and Recovery in Agentic Systems
This addresses operational failures in tool-using agents for developers and researchers, but it is incremental as it focuses on benchmarking rather than solving the underlying issues.
The paper tackles the problem of tool misuse and recovery in agentic systems by introducing ToolMisuseBench, an offline deterministic benchmark that evaluates these issues under explicit budgets, reporting success rates and recovery quality with baseline results showing limited overall success.
Tool using agents often fail for operational reasons even when language understanding is strong. Common causes include invalid arguments, interface drift, weak recovery, and inefficient retry behavior. We introduce ToolMisuseBench, an offline deterministic benchmark for evaluating tool misuse and recovery under explicit step, call, and retry budgets. The benchmark covers CRUD, retrieval, file, and scheduling environments with replayable fault injection. It reports success, invalid call behavior, policy violations, recovery quality, and budgeted efficiency. We release a public dataset with 6800 tasks and a reproducible evaluation pipeline. Baseline results show fault specific recovery gains for schema aware methods, while overall success remains limited under the released authorization and hard failure settings.