智能体对齐指数Alignment Index
初步评估Preliminary基于真实 Agent Arena 会话，衡量智能体未经授权操作、错误归因及将未完成任务报告为完成的发生情况。How often agents act without permission, misrepresent what users said, or report unfinished tasks as done, measured in real Agent Arena sessions.
失败行为细分How models fail
各模型在不同信号下最常见的失败行为。百分比表示该模型被标记案例中的行为占比，同一案例可能属于多种行为。The most common failure modes for each model and signal. Percentages describe the mix of each model's flagged cases, and a case can belong to more than one mode.