Join as on April 23-24, 2026 in Prague on an intimate retreat for mobile gaming creatives and performance leaders, where real conversations happen.

先日アプリストア最適化（ASO）からリリースまで一気通貫でいけるウェブサイトAppAgentを公開しました（Google Playは未対応）。GitHubはこちらです。ぜひスターをつけていただけると嬉しいです！https://github.com/ngo275/app-agent 開発に至った経緯僕は趣味でいくつかアプリを作っており、以前、ASOを改善するために、いくつかのASOツールを試してみま

An Android app that can draw over other windows and write to shared storage can slip instructions to the AI agent driving that phone, in text no human eye will ever see. Two more steps, and the same app is running commands on the PC driving the agent. Researchers demonstrated that chain, plus six other attacks, against five open-source mobile agent frameworks: AppAgent, AppAgentX,

An Android app that can draw over other windows and write to shared storage can slip instructions to the AI agent driving that phone, in text no human eye will ever see. Two more steps, and the same app is running commands on the PC driving the agent. Researchers demonstrated that chain, plus six other attacks, against five open-source mobile agent frameworks: AppAgent, AppAgentX,

An Android app that can draw over other windows and write to shared storage can slip instructions to the AI agent driving that phone, in text no human eye will ever see. Two more steps, and the same app is running commands on the PC driving the agent. Researchers demonstrated that chain, plus six other attacks, against five open-source mobile agent frameworks: AppAgent, AppAgentX,

An Android app that can draw over other windows and write to shared storage can slip instructions to the AI agent driving that phone, in text no human eye will ever see. Two more steps, and the same app is running commands on the PC driving the agent. Researchers demonstrated that chain, plus six other attacks, against five open-source mobile agent frameworks: AppAgent, AppAgentX,

Large language model (LLM)-based agents have demonstrated remarkable capabilities in addressing complex tasks, thereby enabling more advanced information retrieval and supporting deeper, more sophisticated human information-seeking behaviors. However, most existing agents operate in a purely reactive manner, responding passively to user instructions, which significantly constrains their effectiveness and efficiency as general-purpose platforms for information acquisition. To overcome this limitation, this paper proposes AppAgent-Pro, a proactive GUI agent system that actively integrates multi-domain information based on user instructions. This approach enables the system to proactively anticipate users' underlying needs and conduct in-depth multi-domain information mining, thereby facilitating the acquisition of more comprehensive and intelligent information. AppAgent-Pro has the potential to fundamentally redefine information acquisition in daily life, leading to a profound impact on human society. Our code is available at: https://github.com/LaoKuiZe/AppAgent-Pro. The demonstration video could be found at: https://www.dropbox.com/scl/fi/hvzqo5vnusg66srydzixo/AppAgent-Pro-demo-video.mp4?rlkey=o2nlfqgq6ihl125mcqg7bpgqu&st;=d29vrzii&dl;=0.

The OpenClaw platform provides a practical foundation for automation through its skill-oriented architecture, organizing external capabilities into lightweight, reusable components that can be invoked efficiently through a command-line interface (CLI). However, a significant bottleneck remains: m...

PyTorchKR🔥🇰🇷 💬 12/18~24의 주요 ML 논문에 소개된 AppAgent 모델을 정리해보았습니다. 멀티모달 분야에서의 대규모 모델들(LMM)의 연구/공개 따라 이와 같은 '에이전트'들이 더 많이 등장할 것 같습니다. 이 글은 GPT 모델로 자동 요약한 설명으로, 잘못된 내용이 있을 수 있으니 원문을 참고해주세요! 😄 읽으시면서 어색하거나 잘못된 내용을 발견하시면 덧글로 알려주시기를 부탁드립니다! 🙇 소개 AppAgent는 대규모 언어 모델(Large Language Models, LLMs)의 능력을 활용하여 인간과 유사하게 스마트폰 애플리케이션을 운영하는 새로운 멀티모달 에이전트 프레임워크입니다. AppAgent는 독자적인 탐험 또는 인간의 시연을 관찰하며 새로운 스마트폰 앱의 사용법을 학습하고, 이를 통해 다양한 애플리케이션에서 작업을 실행하기 위해 참조할 수 있는 지식(KB; Knowle...

이 글은 GPT 모델로 자동 요약한 설명으로, 잘못된 내용이 있을 수 있으니 원문을 참고해주세요! 😄 읽으시면서 어색하거나 잘못된 내용을 발견하시면 덧글로 알려주시기를 부탁드립니다! 🙇 소개 이번 주에 선정된 논문들을 살펴보면, 대부분 자연어 처리(Natural Language Processing, NLP)와 관련된 주제가 주를 이루는 듯 합니다. "Gemini’s Language Abilities", "LLM in a Flash", "ReST Meets ReAct", "Adversarial Attacks on GPT-4", "RAG for LLM" 그리고 "Findings of the BabyLLM Challenge" 등과 같은 제목에서 알 수 있듯이, 다양한 언어 모델과, 그에 대한 새로운 기법 또는 보안 취약점과 같은 이슈에 대한 연구가 진행되고 있습니다. 특히, GPT-4와 같이 최신의 대형 언어 모델에 대한 연구가 주목되며, 이들 모델...

AppAgent: Multimodal Agents as Smartphone Users, an LLM-based multimodal agent framework designed to operate smartphone apps. - mnotgod96/AppAgent

A novel LLM-based multimodal agent framework designed to operate smartphone applications - GitHub - mnotgod96/AppAgent: A novel LLM-based multimodal agent framework designed to operate smartphone a...