发表机构
Johns Hopkins University; Amazon AGI（约翰霍普金斯大学; 亚马逊AGI）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
EchoPath将GUI智能体的验证轨迹转化为可重放的可调用记忆，通过图像目标重瞄准算法实现确定性重放，显著降低令牌成本与执行时间。
AI 中文摘要
计算机使用智能体越来越多地通过命令行界面（CLI）或应用程序接口（API）门户操作浏览器、软件和桌面应用程序，但图形用户界面（GUI）在常见的工业生产场景中仍然扮演着重要角色。GUI智能体通常采用全新的“观察-规划-落地-执行”循环，这对于企业任务而言效率低下，因为这些任务需要反复更新记录、处理表单、配置工具和导出报告。我们提出EchoPath，一个与模型无关的框架，它将经过工件验证的GUI轨迹转换为标准化、参数可控的可调用记忆，类似于模型上下文协议（MCP）风格的工具调用，而非非结构化的经验记录。每条记忆存储任务意图键、应用程序和状态前置条件、灵活的输入参数、GUI证据、验证来源和生命周期状态，因此宿主智能体仅在当前运行时能够确定性重放时才会调用特定过程。实现重放的核心机制是一种基于图像的目标重新瞄准算法，该算法将存储的坐标视为视觉证据，将记忆的GUI目标与当前屏幕进行匹配，并在执行前输出修正后的操作坐标。在重放过程中，EchoPath仅重新绑定声明的可修改输入，并拒绝模糊或不兼容的步骤，以进行有界的接地修复或重新规划。在真实计算机使用任务的实验中，EchoPath将中位令牌成本降低了90%以上，中位执行时间降低了约60%。这些结果支持一种有界的企业GUI记忆形式：经过验证的执行经验可以成为重复性工作的可控可调用资产，而不仅仅是另一次推理过程的上下文。
英文摘要
Computer-use agents increasingly operate browsers, software, and desktop applications via CLI or API portals, but graphical user interface (GUI) still plays an important role in common industrial production scenarios. GUI agents commonly employ fresh observe-plan-ground-act loops, which is inefficient for enterprise tasks that repeatedly update records, process forms, configure tools, and export reports. We introduce EchoPath, a model-agnostic harness that converts artifact-validated GUI trajectories into standardized, parameter-controlled callable memories, analogous to Model Context Protocol (MCP)-style tool calls rather than unstructured experience records. Each memory stores task-intent keys, application and state preconditions, flexible input parameters, GUI evidence, validation provenance, and lifecycle state, so the host agent invokes a targeted procedure only when it can be deterministically replayed in the current runtime. The core mechanism enabling replay is an image-based target-reaiming algorithm that treats stored coordinates as visual evidence, matches the remembered GUI target against the current screen, and emits corrected operation coordinates before execution. During replay, EchoPath rebinds only declared modifiable inputs and rejects ambiguous or incompatible steps to bounded grounding repair or fresh planning. In experiments with real computer-use tasks, EchoPath reduced median token cost by more than 90% and median execution time by about 60%. These results support a bounded form of enterprise GUI memory: validated execution experience can become a controllable callable asset for recurrent work rather than only context for another reasoning pass.
