1
AlloBench: Measuring Online Tool Allocation Capability in LLM Agents
首个衡量LLM智能体在线工具分配能力的基准，为评估Agent实用性提供新维度。
arXiv:2607.23332v1 Announce Type: new Abstract: Creating a reusable tool is an investment: an agent pays a fixed cost now in exchange for the potentia…