Related papers: CHOP: Mobile Operating Assistant with Constrained …
Businesses and software platforms are increasingly turning to Large Language Models (LLMs) such as GPT-3.5, GPT-4, GLM-3, and LLaMa-2 for chat assistance with file access or as reasoning agents for customer service. However, current…
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…
Agents centered around Large Language Models (LLMs) are now capable of automating mobile device operations for users. After fine-tuning to learn a user's mobile operations, these agents can adhere to high-level user instructions online.…
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…
In this work, we address the cooperation problem among large language model (LLM) based embodied agents, where agents must cooperate to achieve a common goal. Previous methods often execute actions extemporaneously and incoherently, without…
Autonomous agents powered by large language models (LLMs) have shown impressive capabilities in tool manipulation for complex task-solving. However, existing paradigms such as ReAct rely on sequential reasoning and execution, failing to…
Vision-Language Models (VLM) can generate plausible high-level plans when prompted with a goal, the context, an image of the scene, and any planning constraints. However, there is no guarantee that the predicted actions are geometrically…
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…
The attainment of autonomous operations in mobile computing devices has consistently been a goal of human pursuit. With the development of Large Language Models (LLMs) and Visual Language Models (VLMs), this aspiration is progressively…
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…
Advancements in technology, pilot shortages, and cost pressures are driving a trend towards single-pilot and even remote operations in aviation. Considering the extensive workload and huge risks associated with single-pilot operations, the…
Our research investigates the capability of modern multimodal reasoning models, powered by Large Language Models (LLMs), to facilitate vision-powered assistants for multi-step daily activities. Such assistants must be able to 1) encode…
The utilisation of foundation models as smartphone assistants, termed app agents, is a critical research challenge. These agents aim to execute human instructions on smartphones by interpreting textual instructions and performing actions…
Planning is a crucial task for agents in task oriented dialogs (TODs). Human agents typically resolve user issues by following predefined workflows, decomposing workflow steps into actionable items, and performing actions by executing APIs…
Cooperative multi-agent reinforcement learning (MARL) struggles with sample efficiency, interpretability, and generalization. While Large Language Models (LLMs) offer powerful planning capabilities, their application has been hampered by a…
In orchestrated multi-agent systems, humans often struggle to manage plans due to their complexity and limited transparency. Existing approaches rely on outcome-level supervision, where users verify only final outputs without visibility…
Intelligent interaction with the real world requires robotic agents to jointly reason over high-level plans and low-level controls. Task and motion planning (TAMP) addresses this by combining symbolic planning and continuous trajectory…
Task planning and motion planning are two of the most important problems in robotics, where task planning methods help robots achieve high-level goals and motion planning methods maintain low-level feasibility. Task and motion planning…
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…
The integration of Large Language Models (LLMs) with microscopic traffic simulation offers a promising path toward autonomous urban planning and intelligent transportation analysis. However, existing monolithic agent architectures often…