AI 干活达标了，但没伺候好你
现在的 AI 操作电脑，评测标准是「任务完成没」，可真实用户会漏说要求、加限制、要审批。这篇把同一批任务换成 44 种真人语气重写，AI 只看到对话、看不到原始指令，结果任务完成率平均掉 36%。更扎心的是，即便任务全做完，用户给满分好评的比例也从 84% 掉到 63%——AI 按字面干完了活，却没接住你话里的潜台词。它不是你明天能用上的东西，但提醒你：别把「AI 做完了」当成「AI 做对了」。
📄 原文摘要(英文)
Computer-use agents (CUAs) are commonly evaluated against fixed task specifications, but users may omit requirements, add constraints, or require approval before consequential actions. Completing the benchmark instruction does not guarantee serving the person who asked. We introduce PersonaCUABench, which holds 74 tasks across 11 domains fixed and varies only who asks. A persona agent, playing one of 44 personas in four groups, rewrites each instruction in that user's own words and answers the CUA's questions, while the CUA sees only the dialogue, never the profile or the original instruction. Across nine backbones (3,330 runs), mean task completion falls by 36% relative to the original requests. The losses have two sources: in 59.9% of cells that lose points, the agent engages with what the user asked for and still gets it wrong, and 11.2% are stops the user requested that the checker scores as failures. Even when a persona request is fully completed, the user gives the top satisfaction rating in only 62.7% of cells, against 84.1% for the original requests. CUAs should therefore be evaluated not only on task completion but also on whether they meet the requirements and constraints users express. Code: https://github.com/MatrAIx-ai/PersonaCUABench. Project page: https://matraix.ai/research/persona-cua.html