arXiv cs.AI· Ziyang Chen, Qian Li, Chengwei Qin·· 13 小时前AI 评分34
TAM：以任务推进状态与监督提升 GUI 智能体能力
From Interaction to Capability: Task Advancement as State and Supervision for GUI Agents
AI 导读
研究提出 Task Advancement Memory（TAM），将任务推进定义为经核验的任务进度，在执行中维护 Advancement State 并抽象出可复用操作。
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