Glossary · Objects and system context
Dual-control environment
An interactive environment in which both the agent and a simulated user act through tools on a shared world, each with its own state and toolset, so success depends on coordination and guidance, as in τ²-bench.
Defined in
Handbook · Agents and self-improvementEvaluating agentsAn agent is a trajectory through a changing world. Evaluate outcome, path, permissions, side effects and honesty, not a final answer.Related terms
- Simulated user
- A language model, prompted with personas mined from real conversation logs, that plays the user in multi-turn evals. It is environment, not system: its quirks can create fake failures and fake passes, and it drifts like a judge.