KnowAct-GUIClaw：深度认知，完美执行——具备自进化记忆与技能的个人GUI助手

摘要

OpenClaw已成为复杂任务自动化领域的领先智能体框架，但其在跨平台GUI交互支持与完善的自我进化机制方面仍存在不足。这些缺陷限制了它对多样化设备生态系统的适应性，并阻碍了通过持续从执行经验中学习来提升性能。为解决这些问题，我们提出了面向个人助手的"深度认知、完美行动"范式，该范式认为积累的用户交互与任务运行经验可直接提升执行准确性与效率，统一了认知理解与操作执行。基于这一范式，我们提出了KnowAct-GUIClaw——一种新颖的"知识-路由-行动-反思"框架，旨在弥补OpenClaw在GUI操作上的缺陷，突破其跨平台与递归式自我改进的瓶颈。首先，主智能体利用积累的交互经验与任务相关知识进行长周期任务分解与分配（Know）。其次，一个可插拔的GUI子智能体配备经验可归因记忆系统（Know）与自我进化的技能库（Act），从而实现无缝跨平台迁移与快速路径集成。特别地，该框架持续存储用户画像与反馈，以提升任务分解与工具调用的准确性。在Android、iOS、HarmonyOS及Windows平台上的大量实验表明，KnowAct-GUIClaw在效率、准确性与跨平台适应性方面均表现优异。尤其值得关注的是，基于开源Kimi-2.6模型的GUIClaw在长周期MobileWorld基准上取得了最佳性能（64.1%），超越了所有智能体框架及闭源智能体模型（如Seed-2.0-Pro与GPT-5.5）。此外，本框架所支持的知识型记忆与执行技能可跨多种基座模型迁移，在Kimi-2.6上带来8.5%的性能提升。

English

OpenClaw has emerged as a leading agent framework for complex task automation, yet it faces insufficient cross-platform GUI interaction support and a well-built self-evolution mechanism. These flaws limit its adaptation to diverse device ecosystems and prevent performance improvements through continuous learning from execution experience. To resolve these issues, we propose the Know Deeply, Act Perfectly paradigm for personal assistants, which holds that accumulated user interaction and task-running experience directly improve execution accuracy and efficiency, unifying cognitive comprehension and operational execution. Based on this paradigm, we introduce KnowAct-GUIClaw, a novel Know-Route-Act-Reflect framework designed to address OpenClaw's GUI manipulation deficits and break through its cross-platform and recursive self-improvement constraints. First, the host agent leverages accumulated interaction experience and task-relevant knowledge for long-horizon task decomposition and allocation (Know). Second, a pluggable GUI subagent with an experience-attributable memory system (Know) and self-evolving skill library (Act), enabling seamless cross-platform migration and fast-path integration. Especially, this framework continuously stores user profiles and feedback to improve the accuracy of task decomposition and tool calls. Extensive experiments across Android, iOS, HarmonyOS and Windows show that KnowAct-GUIClaw achieves superior efficiency, accuracy and cross-platform adaptability. Especially, the GUIClaw with open-source Kimi-2.6 models achieves the best performance (64.1%) on the long-horizon MobileWorld benchmark, beating all agentical frameworks and closed-source agentical models, e.g., Seed-2.0-Pro and GPT-5.5. Additionally, the knowledgeable memory and execution skills supported by our framework are transferable across diverse base models, improving by 8.5% with Kimi-2.6.

KnowAct-GUIClaw：深度认知，完美执行——具备自进化记忆与技能的个人GUI助手

KnowAct-GUIClaw: Know Deeply, Act Perfectly, Personal GUI Assistant with Self-Evolving Memory and Skill

摘要

Support