Related papers: K^2-Agent: Co-Evolving Know-What and Know-How for …

Building agents that autonomously operate mobile devices has attracted increasing attention. While Vision-Language Models (VLMs) show promise, most existing approaches rely on direct state-to-action mappings, which lack structured reasoning…

Smartphones have become indispensable in modern life, yet navigating complex tasks on mobile devices often remains frustrating. Recent advancements in large multimodal model (LMM)-based mobile agents have demonstrated the ability to…

In the field of MLLM-based GUI agents, compared to smartphones, the PC scenario not only features a more complex interactive environment, but also involves more intricate intra- and inter-app workflows. To address these issues, we propose a…

Large language model (LLM)-based agents have shown strong potential in multi-task scenarios, owing to their ability to transfer knowledge across diverse tasks. However, existing approaches often treat prior experiences and knowledge as…

Reinforcement learning (RL) agent development traditionally requires substantial expertise and iterative effort, often leading to high failure rates and limited accessibility. This paper introduces Agent$^2$, an LLM-driven…

Mobile device operation tasks are increasingly becoming a popular multi-modal AI application scenario. Current Multi-modal Large Language Models (MLLMs), constrained by their training data, lack the capability to function effectively as…

Computer use agents automate digital tasks by directly interacting with graphical user interfaces (GUIs) on computers and mobile devices, offering significant potential to enhance human productivity by completing an open-ended space of user…

Controlling desktop applications via software remains a fundamental yet under-served problem. Existing multi-modal large language models (MLLMs) ingest screenshots and task instructions to generate keystrokes and mouse events, but they…

Mobile agents show immense potential, yet current state-of-the-art (SoTA) agents exhibit inadequate success rates on real-world, long-horizon, cross-application tasks. We attribute this bottleneck to the agents' excessive reliance on…

Effective human-robot collaboration (HRC) requires translating high-level intent into contact-stable whole-body motion while continuously adapting to a human partner. Many vision-language-action (VLA) systems learn end-to-end mappings from…

Large Language Models (LLMs) have demonstrated great potential in complex reasoning tasks, yet they fall short when tackling more sophisticated challenges, especially when interacting with environments through generating executable actions.…

Recent advances in Multimodal Large Language Models (MLLMs) have enabled the development of mobile agents that can understand visual inputs and follow user instructions, unlocking new possibilities for automating complex tasks on mobile…

K2-Think is a reasoning system that achieves state-of-the-art performance with a 32B parameter model, matching or surpassing much larger models like GPT-OSS 120B and DeepSeek v3.1. Built on the Qwen2.5 base model, our system shows that…

Mobile GUI agents exhibit substantial potential to facilitate and automate the execution of user tasks on mobile phones. However, exist mobile GUI agents predominantly privilege autonomous operation and neglect the necessity of active user…

While large language model-based multi-agent systems have shown strong potential for complex reasoning, how to effectively organize multiple agents remains an open question. In this paper, we introduce OrgAgent, a company-style hierarchical…

Recent advances in vision-language models have enabled mobile GUI agents to perceive visual interfaces and execute user instructions, but reliable prediction of action consequences remains critical for long-horizon and high-risk…

Recent advancements in large language models (LLMs) have led to the creation of intelligent agents capable of performing complex tasks. This paper introduces a novel LLM-based multimodal agent framework designed to operate smartphone…

Vision-language model-based mobile agents have gained the ability to understand complex instructions and mobile screenshots, benefiting from reinforcement learning paradigms like Group Relative Policy Optimization (GRPO). However, existing…

Large Language Model (LLM)-based mobile agents have made significant performance advancements. However, these agents often follow explicit user instructions while overlooking personalized needs, leading to significant limitations for real…

To tackle increasingly complex tasks, recent research on mobile agents has shifted towards multi-agent collaboration. Current mobile multi-agent systems are primarily deployed in the cloud, leading to high latency and operational costs. A…