KnowAct-GUIClaw: Know Deeply, Act Perfectly, Personal GUI Assistant with Self-Evolving Memory and Skill
:::info Stub — Full Engineering Breakdown Coming This paper was featured on Hugging Face Daily Papers on 2026-07-15 with 56 upvotes. A full breakdown with production viability rating, implementation notes, and honest limitations is being written. Subscribe to AI Letters → :::
| Authors | Yunxin Li et al. |
| Year | 2026 |
| HF Upvotes | 56 |
| arXiv | 2607.12625 |
| Download | |
| HF Page | View on Hugging Face |
Abstract
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.
Engineering Breakdown
The Problem
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.
The Approach
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. 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.
Key Results
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. Especially, this framework continuously stores user profiles and feedback to improve the accuracy of task decomposition and tool calls.
Research Areas
This paper contributes to the following areas of AI/ML engineering:
- Machine learning
- Deep learning
- Neural networks
- Model optimization
- AI systems
- Knowactguiclaw
:::tip Subscribe Get weekly breakdowns of papers like this in AI Letters - the newsletter for engineers building production AI systems. :::