#artificial intelligence
May 2026
AsyncTool: Evaluating the Asynchronous Function Calling Capability under Multi-Task Scenarios
This work proposes AsyncTool, a benchmark for assessing LLM-based agents in interactive multi-task tool-use environments with delayed tool feedback, and constructs a diverse asynchronous multitasking dataset that covers multiple scenarios and tool-use patterns.
Kou Shi, Ziao Zhang, Shi-Ting Huang et al.
· arXiv.org · 3 citations