提出任务状态表征，让手机端智能体长期执行更可靠。
A Task-State Representation for Long-Horizon Mobile GUI Agents
- 用外部组件分离任务状态与屏幕信息，避免记忆混淆。
- 在复杂跨应用任务中，成功率最高提升12个百分点。
- 无需修改模型结构，适合各类手机自动化场景。
长时程手机图形界面智能体通常依赖思考-行动-观察循环，但难以区分持久的任务状态与瞬时的屏幕观测。随着执行历史增长，二者纠缠导致严重上下文负担，使智能体遗忘初始要求、虚构进展或重复操作过时界面。为此，我们提出任务状态表征（TSR），一种无需训练的框架，显式解耦任务状态与感知输入。作为轻量级外部封装，TSR维护三个结构化组件：全局指令摘要、子目标动态进度追踪器和过渡感知动作验证器。通过前后动作的视觉对比持续更新，有效引导智能体推理，无需架构改动。在四个手机图形界面基准上实验验证，TSR在复杂跨应用和高记忆需求任务中，成功率最高提升12个百分点。
原文摘要 · Abstract (English)
While long-horizon mobile GUI agents typically rely on thought-action-observation loops, they struggle to separate persistent task states from transient screen observations. As execution histories grow, this entanglement imposes a severe context burden, causing agents to forget initial requirements, hallucinate progress, or repeatedly interact with stale interfaces. To address this, we introduce Task-State Representation (TSR), a training-free framework that explicitly decouples task state from sensory input. Acting as a lightweight external wrapper, TSR maintains three structured components: a global instruction summary, a dynamic progress tracker for subgoals, and a transition-aware action verifier. By continuously updating through pre- and post-action visual comparisons, TSR effectively guides the agent's reasoning without requiring architectural modifications. Experiments across four mobile GUI benchmarks validate TSR's effectiveness, yielding up to a 12 absolute point increase in success rate on complex cross-application and memory-intensive tasks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。