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

Manipulation and locomotion are closely related problems that are often studied in isolation. In this work, we study the problem of coordinating multiple mobile agents to exhibit manipulation behaviors using a reinforcement learning (RL)…

Large language model based multi-agent systems have demonstrated significant potential in social simulation and complex task resolution domains. However, current frameworks face critical challenges in system architecture design,…

Multimodal Large Language Models (MLLMs) based agents have demonstrated remarkable potential in autonomous web navigation. However, handling long-horizon tasks remains a critical bottleneck. Prevailing strategies often rely heavily on…

Agentic AI has significantly extended the capabilities of large language models (LLMs) by enabling complex reasoning and tool use. However, most existing frameworks are tailored to domains such as mathematics, coding, or web automation, and…

In this paper, we aim to improve the reasoning ability of large language models (LLMs) over knowledge graphs (KGs) to answer complex questions. Inspired by existing methods that design the interaction strategy between LLMs and KG, we…

Mobile agents powered by vision-language models have demonstrated impressive capabilities in automating mobile tasks, with recent leading models achieving a marked performance leap, e.g., nearly 70% success on AndroidWorld. However, these…

Mobile device agent based on Multimodal Large Language Models (MLLM) is becoming a popular application. In this paper, we introduce Mobile-Agent, an autonomous multi-modal mobile device agent. Mobile-Agent first leverages visual perception…

This technical brief introduces Deep Agent, an advanced autonomous AI system designed to manage complex multi-phase tasks through a novel hierarchical task management architecture. The system's foundation is built on our Hierarchical Task…

With the advancement of Multimodal Large Language Models (MLLM), LLM-driven visual agents are increasingly impacting software interfaces, particularly those with graphical user interfaces. This work introduces a novel LLM-based multimodal…

The paper introduces GUI-Owl-1.5, the latest native GUI agent model that features instruct/thinking variants in multiple sizes (2B/4B/8B/32B/235B) and supports a range of platforms (desktop, mobile, browser, and more) to enable cloud-edge…

Communication is essential in coordinating the behaviors of multiple agents. However, existing methods primarily emphasize content, timing, and partners for information sharing, often neglecting the critical aspect of integrating shared…

Recently, mobile AI agents have gained increasing attention. Given a task, mobile AI agents can interact with mobile devices in multiple steps and finally form a GUI flow that solves the task. However, existing agents tend to focus on most…

Symbolic world models (e.g., PDDL domains or executable simulators) are central to model-based planning, but training LLMs to generate such world models is limited by the lack of large-scale verifiable supervision. Current approaches rely…

Autonomous GUI agents interact with environments by perceiving interfaces and executing actions. As a virtual sandbox, the GUI World model empowers agents with human-like foresight by enabling action-conditioned prediction. However,…

In collaborative tasks, autonomous agents fall short of humans in their capability to quickly adapt to new and unfamiliar teammates. We posit that a limiting factor for zero-shot coordination is the lack of shared task abstractions, a…

In this work, we propose MetaAgent, an agentic paradigm inspired by the principle of learning-by-doing, where expertise is developed through hands-on practice and continual self-improvement. MetaAgent starts with a minimal workflow,…

With the advancement of vision-language models, web automation has made significant progress. However, deploying autonomous agents in real-world settings remains challenging, primarily due to site heterogeneity, where generalist models lack…

Mobile phone agents can assist people in automating daily tasks on their phones, which have emerged as a pivotal research spotlight. However, existing procedure-oriented agents struggle with cross-app instructions, due to the following…

The effectiveness of LLM-based agents is often limited not by model capacity alone, but by how efficiently contextual information is utilized at runtime. Existing agent frameworks rely on rigid, syntax-heavy state representations such as…

Large Language Model (LLM)-based agents exhibit significant potential across various domains, operating as interactive systems that process environmental observations to generate executable actions for target tasks. The effectiveness of…