稳定报道时间 2026-10-02 12:00
BACKDROP 评估智能体在动态环境中的性能
BACKDROP 是一个新的基准，通过在执行环境中引入日常危害来测试 AI 代理在动态、现实世界环境中的表现。
01
证据
- AarXiv cs.CL研究机构2026-10-02 12:00
Abstract: Agent benchmarks test agents in worlds that stay still. Deployed agents work in worlds that other people also change. Someone texts the agent to send…