微软 TeleTune：从原始使用日志学习智能体技能
New Microsoft paper shows that agents can learn software skills from raw usage logs by keeping only skill edits that better predict users' next actions.
微软论文提出 TeleTune，让智能体从原始使用日志中学习软件技能，只保留能更好预测用户下一步动作的技能编辑。该方法无需实时测试环境，因为旧日志上的下一动作准确率与线上成功率一致；它先猜测每个会话的目标，再用文本技能库预测日志中的每个动作，错误猜测触发库编辑，仅在留出日志上准确率提升时保留。此前 Agent Workflow Memory 等方法需要目标标注样本或实时环境。
正文
当前显示原文，中文全文译文尚未就绪。
New Microsoft paper shows that agents can learn software skills from raw usage logs by keeping only skill edits that better predict users' next actions.
i.e. You do not need a live test environment to check whether a new agent skill helps, because next-action accuracy on old logs tracked live success.
Usage logs hold lots of know-how, but they record no goals, often mix several tasks, and cannot be replayed. Earlier methods, like Agent Workflow Memory, need goal-labeled examples or a live environment to test changes.
TeleTune guesses each session's goal and has the model predict every logged action using a text skill library. Wrong guesses suggest library edits, and an edit stays only if accuracy rises on held-out logs.
If your product records user activity, mine it for agent skills and judge each change by next-action accuracy on held-out logs.
– arxiv. org/abs/2610.05437