---
title: "从计算机使用轨迹中归纳任务模型"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2608.20319v1"
permalink: "https://feed.astralor.com/items/itm_023f777f7dba46bb1825923d"
published: "2026-08-20T17:57:00.000Z"
score: 76
channel: "ai"
tags: ["arXiv","TMI","任务模型归纳","计算机使用智能体","轨迹学习"]
---

# 从计算机使用轨迹中归纳任务模型

## AI 点评

> 这篇论文值得关注，因为它抓住了智能体落地真实工作时的一个关键痛点：如何从杂乱的轨迹中提炼可审计的结构化知识。对做智能体学习或企业流程自动化的人来说，TMI提出了一条可行路径，而且实验数字很漂亮，建议细读方法部分看它在复杂真实环境下的扩展性。

## 速览

该论文提出任务模型归纳（TMI）框架，用于从被动记录的自然计算机使用轨迹中提取可审计、可复用的符号化任务模型。与现有方法不同，TMI无需预设任务或工作流，能够自动发现轨迹中隐藏的并发任务，并为每个任务构建分层目标模型与控制流程序模型。在受控的人类与智能体轨迹上，TMI恢复了交错任务，与真实分组的一致性达0.974，重构了74.9%的观察执行步骤；下游任务中，基于TMI任务模型提取的技能将任务准确率提升30.0%。

## 关键点

- TMI无需预设任务或工作流，从原始轨迹中自动发现并分离并发任务。
- 为每个潜在任务构建分层目标模型与控制流程序模型。
- 在受控实验中，任务分组一致性达0.974，步骤重构率达74.9%。
- TMI任务模型衍生的技能使下游任务准确率提升30.0%。

## 全文

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.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_023f777f7dba46bb1825923d