Inducing Task Models from Computer-Use Traces

2026-08-20

AI Summary

研究提出任务模型归纳法，从自然计算机使用痕迹中提取多线程工作流程，解决现有方法仅能处理单一工作流的问题。

Abstract

Naturalistic computer-use traces, passively recorded screenshots and mouse or keyboard actions, are a valuable resource for deriving symbolic, auditable, and reusable models of how everyday work is done. Such models matter as computer-use agents enter real work, where agents need to learn how tasks are actually performed, and organizations need to audit and reuse that knowledge. However, inducing such task models is challenging, as activity is observed only as low-level events and real-world work is multi-threaded with interleaved goals. Existing methods assume a given task or a single workflow, and produce step-level summaries rather than structured task models. We introduce Task Model Induction (TMI), which (i) discovers the latent tasks in an unconstrained trace, disentangling concurrent activity, and (ii) for each latent task, induces a task model pairing a hierarchical objective model of recursive goal decomposition with a procedure model of the control flow that organized the execution. Intrinsically, on controlled human and agent trajectories, TMI recovers interleaved tasks with 0.974 agreement against ground-truth groupings and reconstructs 74.9% of the observed execution steps, far more than the strongest workflow induction baseline. Extrinsically, skills derived from TMI's task models improve held-out task accuracy by 30.0% over the strongest baseline.

Problem

• Task Model Induction
• Computer-Use Traces
• Hierarchical Objective Model
• Procedure Model
• Interleaved Goals

Innovation

• Task Model Induction
• latent tasks
• hierarchical objective model
• control flow
• naturalistic computer-use traces