From Interaction to Capability: Task Advancement as State and Supervision for GUI Agents· 从交互到能力：GUI 代理的任务进展记忆
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 out
提出 GUI 代理的 TAM 模型，从交互中学习并记忆任务进展。
- 核心方法
- 引入任务进展记忆 (TAM)，使用任务进展状态表示已验证的任务进度如何改变剩余目标，并通过进展监督识别和抽象产生局部结果的交互。
- 适合谁读
- 适合 AI 领域的研究者和工程师，尤其是关注 GUI 代理及长期任务处理的人员。
- 要解决的问题
- 在长时间的工作流程中，GUI 代理难以跨应用保留过去行动的结果并学习可重用的操作。
- 关键实验
- 未提供
- 主要贡献
- TAM 模型支持GUI代理的持续任务执行和可重用操作的学习，增强了代理在长时间工作流程中的适应性和效率。
- 意义与局限
- 意义在于提高了GUI代理在复杂任务中的表现，但可能受限于任务进度验证的准确性和抽象能力。