微软提出OAT：用成功轨迹训练轻量级属性器调试Agent
微软新论文提出OAT，用成功轨迹就能定位Agent失败步骤，不用费钱费力的错误标注，思路很巧妙。
微软等机构在论文中提出OAT（One-class Attribution for Trajectories），一种轻量级属性器。
它仅需成功轨迹训练，通过神经控制微分方程建模成功轨迹的动力学。然后识别失败轨迹中偏离成功流的步骤，实现故障归因。
不需要失败数据或错误标签，避免了昂贵的提示管道或后训练。论文编号2607.
12747。
NEW paper from Microsoft and colleagues. Debugging agent trajectories at scale is challenging. This is a clever approach to monitor and improve agents in production. The problem: Finding which step in a failed agent run caused the failure usually means one of two costly options. Run an expensive prompting pipeline over the whole trajectory, or post-train on failure data with step-level error labels that are hard to collect and difficult to scale. The solution: They propose OAT, a lightweight attributor that needs neither. It trains only on successful trajectories, models their dynamics with neural controlled differential equations, then flags the steps where a failure trajectory departs from that learned flow of success. Failure attribution becomes one-class learning over what success looks like, so you never need labeled error steps or failure data at all. Paper: arxiv.org/abs/2607.12747 Learn to build effective AI agents in our academy: academy.dair.ai📊 13 ⚡
This report is categorized under AITOP's "Papers" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Key entities and technical topics under continuous tracking include Microsoft, OAT, 智能体, 调试.
Source attribution: curated from elvis (@omarsar0).
