2 papers
cs.AI2026
AppWorld-UL: Benchmarking Diverse Agent-User Interactions for Tool-Use
Junzhi Chen, Harsh Trivedi, Jane Pan +4
Tool-use agents that address day-to-day digital tasks such as ordering groceries must not only operate applications, but also interact with the user, e.g., to ask clarification que…
cs.CL2025
Smurfs: Multi-Agent System using Context-Efficient DFSDT for Tool Planning
Junzhi Chen, Juhao Liang, Benyou Wang
Teaching large language models (LLMs) to use tools for solving complex problems can grant them human-like reasoning abilities. ReAct and its variants are popular frameworks for too…