AI学会的工作技能，换个人就废了
大模型智能体正在学习「肌肉记忆」——记住重复性工作步骤来提升效率。但一篇新研究揭示了一个反直觉的真相：这些技能可能只对特定岗位有效，换个角色就失灵。研究者构建了包含382个企业任务的基准测试，覆盖6种职业角色和22项技能。他们发现，AI通过一次优化就能将任务表现提升3.7-6.7个百分点，且从多个模型执行轨迹中提炼的技能，跨模型准确率可达73.1%。然而，有些技能能广泛迁移，另一些则高度专业化——比如财务专员的技能换到客服岗位，效果大打折扣。这提醒我们：部署AI助手时，不能指望一套技能包打天下，需要根据角色定制和评估。
📄 原文摘要(英文)
Procedural memory is increasingly used to improve LLM agents on recurring workplace tasks, yet its ability to produce reusable skills remains poorly understood. We introduce AFTER, a benchmark of 382 realistic enterprise tasks spanning six professional roles and 22 procedural skills, designed to evaluate how skills transfer across tasks, roles, and model backbones. The benchmark includes controlled evaluation settings for local improvement, cross-task transfer, cross-role transfer, and cross-model generalization. Experiments show that procedural memory delivers consistent gains in industrial workflows: a single refinement round improves aggregate performance by 3.7-6.7 points, while skills evolved from diverse multi-model execution traces achieve 73.1% cross-model test accuracy, outperforming all single-model trace sources. We further find that some skills generalize broadly across tasks and models, whereas others become specialized to role-specific workflows and lose effectiveness under transfer. These results provide practical guidance for building, evaluating, and deploying procedural memory systems in production agent platforms.