paper-with-me

Papers

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

2026-07-14 · Yunxin Li, Jinchao Li, Shibo Su, Zhenran Xu, Chenrui Zhao, Tongshu Bian, Xiaoman Liang, Meishan Zhang, Baotian Hu, Min Zhang arxiv

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.

📄 PDF Abstract BibTeX arXiv:2607.12625

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Secure & Personalized Music-to-Video Generation via CHARCHA

2025-02-03 · Mehul Agarwal, Gauri Agarwal, Santiago Benoit, Andrew Lippman 외

Music is a deeply personal experience and our aim is to enhance this with a fully-automated pipeline for personalized music video generation. Our work allows listeners to not just be consumers but co-creators in the musi…

RhythmVideo Generation

Echo-N1: Affective RL Frontier

2025-11-29 · Naifan Zhang, Ruihan Sun, Ruixi Su, Shiqi Ma 외 arxiv

The LLM field has spent a year perfecting RL for tasks machines already excel at, math, code, and deterministic reasoning, while completely sidestepping the domain that actually defines human intelligence: subjective, em…

Emotional Intelligence

MobileMem: Learning from a Year of Mobile Experiences

2026-08-11 · Xinle Deng, Yida Xue, Xiangyuan Ru, Haoming Xu 외 hf

The next generation of AI agents is increasingly moving beyond systems that answer isolated questions toward persistent personal assistants that can understand, remember, and continuously learn from users' experiences. S…

Information Retrieval

Learning to Rank Personalized Search Results in Professional Networks

2016-05-16 · Viet Ha-Thuc, Shakti Sinha

LinkedIn search is deeply personalized - for the same queries, different searchers expect completely different results. This paper presents our approach to achieving this by mining various data sources available in Linke…

Learning-To-Rank

Modular Clinical Decision Support Networks (MoDN) -- Updatable, Interpretable, and Portable Predictions for Evolving Clinical Environments

2022-11-12 · Cécile Trottet, Thijs Vogels, Martin Jaggi, Mary-Anne Hartley

Data-driven Clinical Decision Support Systems (CDSS) have the potential to improve and standardise care with personalised probabilistic guidance. However, the size of data required necessitates collaborative learning fro…

Privacy Preserving