Jul 2026
AppWorld-UL: Benchmarking Diverse Agent-User Interactions for Tool-Use
AppWorld-UL is introduced, a ``user-in-the-loop''benchmark of 516 challenging tasks requiring diverse agent-user interactions that systematically modify original tasks to introduce ambiguities and constraints that necessitate various types of agent-user interaction.
Junzhi Chen, H. Trivedi, Jane Pan et al.
· arXiv.org · 1 citation