TAM：将任务进展作为 GUI Agent 的状态与监督信号
From Interaction to Capability: Task Advancement as State and Supervision for GUI Agents
AI 导读
一项 arXiv 研究提出 Task Advancement Memory（TAM），把已验证的任务进展作为 GUI Agent 的状态表示与学习监督，跨应用支持长程任务执行并沉淀可复用操作。
正文 · 原文
Abstract:GUI memory should preserve the results of past actions and learn reusable operations. This is difficult in long-horizon workflows, where agents must use information across applications and useful operations are interleaved with failed attempts. We introduce Task Advancement Memory (TAM), which defines task advancement as verified task progress, and supports ongoing task execution and learns reusable operations. During execution, Task Advancement State represents how verified task progress changes the remaining goals, allowing the agent to build on earlier achievements across applications. After each task, advancement supervision identifies and abstracts the interactions that produced a verified local result. The learned operations preserve the relation between required inputs, expected outcomes, and verification conditions. This retains locally successful operations from both successful and failed tasks. On MobileWorld GUI-only tasks, Advancement State alone raises success from 12.0% to 28.2%. Full TAM achieves a 17.6% relative gain in task success over the strongest evaluated baseline and reduces lifecycle tokens per solved task by 38.7%. On SPA-Bench, TAM achieves state-of-the-art task success in the single-app English Level 3 setting.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.37482 [cs.AI] |
| (or arXiv:2610.37482v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.37482 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Ziyang Chen [view email]
[v1]
Tue, 27 Oct 2026 16:09:25 UTC (2,675 KB)
来源：arXiv cs.AI · arxiv.org