What it measures
Both agent and simulated user can act on the shared state in technical-support tasks.
How to read the result
Useful for testing when an assistant should instruct the user, act itself, and confirm that an intervention worked.
Limits and comparison traps
A dual-control user simulator changes the interaction. Do not pool this with a single-controller tool benchmark.
Benchmark reference notes
Dual-control conversational benchmark where both the agent and simulated user must execute coordinated actions to fix telecom issues.
Where this fits in an evaluation suite
A transcript that says “done” is weaker evidence than the verified final state. Track policy violations, recoveries, and invalid attempts alongside success.
Start with a capability hypothesis, then choose a second test with a different failure mode. Keep the checkpoint, reasoning effort, agent tools, sampling policy, and scoring procedure fixed when measuring a training intervention. Record failures and missing outputs in the denominator.
A reproducible comparison
Use the exact implementation, version, task subset, tool access, attempt budget, and judge described by the source.
Publish the exact run configuration, item coverage, score units, and available uncertainty. If a source supplies only an aggregate or a single run, preserve that limit. A new model name or a rounded score alone does not establish a capability improvement.
PRIMARY EVIDENCE & FURTHER READING
Reviewed 2026-10-26. Explanation and interpretation by RLTasks. Benchmark ownership remains with its original authors.