MobA: A Two-Level Agent System for Efficient Mobile Task Automation

• URL: http://arxiv.org/abs/2410.13757v1
• Date: Thu, 17 Oct 2024 16:53:50 GMT
• Title: MobA: A Two-Level Agent System for Efficient Mobile Task Automation
• Authors: Zichen Zhu, Hao Tang, Yansi Li, Kunyao Lan, Yixuan Jiang, Hao Zhou, Yixiao Wang, Situo Zhang, Liangtai Sun, Lu Chen, Kai Yu,
• Abstract summary: MobA is a novel Mobile phone Agent powered by multimodal large language models. The high-level Global Agent (GA) is responsible for understanding user commands, tracking history memories, and planning tasks. The low-level Local Agent (LA) predicts detailed actions in the form of function calls, guided by sub-tasks and memory from the GA.
• Score: 22.844404052755294
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Current mobile assistants are limited by dependence on system APIs or struggle with complex user instructions and diverse interfaces due to restricted comprehension and decision-making abilities. To address these challenges, we propose MobA, a novel Mobile phone Agent powered by multimodal large language models that enhances comprehension and planning capabilities through a sophisticated two-level agent architecture. The high-level Global Agent (GA) is responsible for understanding user commands, tracking history memories, and planning tasks. The low-level Local Agent (LA) predicts detailed actions in the form of function calls, guided by sub-tasks and memory from the GA. Integrating a Reflection Module allows for efficient task completion and enables the system to handle previously unseen complex tasks. MobA demonstrates significant improvements in task execution efficiency and completion rate in real-life evaluations, underscoring the potential of MLLM-empowered mobile assistants.

Related papers

• Adaptive Orchestration of Modular Generative Information Access Systems [59.102816309859584]
  We argue that the architecture of future modular generative information access systems will not just assemble powerful components, but enable a self-organizing system. This perspective urges the IR community to rethink modular system designs for developing adaptive, self-optimizing, and future-ready architectures.
  arXiv  Detail & Related papers  (2025-04-24T11:35:43Z)
• Mobile-MMLU: A Mobile Intelligence Language Understanding Benchmark [45.28023118459497]
  We introduce Mobile-MMLU, a large-scale benchmark dataset tailored for mobile intelligence. It consists of 16,186 questions across 80 mobile-related fields, designed to evaluate LLM performance in realistic mobile scenarios. A challenging subset, Mobile-MMLU-Pro, provides advanced evaluation similar in size to MMLU-Pro but significantly more difficult than our standard full set.
  arXiv  Detail & Related papers  (2025-03-26T17:59:56Z)
• Mobile-Agent-E: Self-Evolving Mobile Assistant for Complex Tasks [85.48034185086169]
  Mobile-Agent-E is a hierarchical multi-agent framework capable of self-evolution through past experience. Mobile-Agent-E achieves a 22% absolute improvement over previous state-of-the-art approaches.
  arXiv  Detail & Related papers  (2025-01-20T20:35:46Z)
• SPA-Bench: A Comprehensive Benchmark for SmartPhone Agent Evaluation [89.24729958546168]
  We present SPA-Bench, a comprehensive SmartPhone Agent Benchmark designed to evaluate (M)LLM-based agents. SPA-Bench offers three key contributions: A diverse set of tasks covering system and third-party apps in both English and Chinese, focusing on features commonly used in daily routines. A novel evaluation pipeline that automatically assesses agent performance across multiple dimensions, encompassing seven metrics related to task completion and resource consumption.
  arXiv  Detail & Related papers  (2024-10-19T17:28:48Z)
• Flex: End-to-End Text-Instructed Visual Navigation with Foundation Models [59.892436892964376]
  We investigate the minimal data requirements and architectural adaptations necessary to achieve robust closed-loop performance with vision-based control policies. Our findings are synthesized in Flex (Fly-lexically), a framework that uses pre-trained Vision Language Models (VLMs) as frozen patch-wise feature extractors. We demonstrate the effectiveness of this approach on quadrotor fly-to-target tasks, where agents trained via behavior cloning successfully generalize to real-world scenes.
  arXiv  Detail & Related papers  (2024-10-16T19:59:31Z)
• AppAgent v2: Advanced Agent for Flexible Mobile Interactions [46.789563920416626]
  This work introduces a novel LLM-based multimodal agent framework for mobile devices. Our agent constructs a flexible action space that enhances adaptability across various applications. Our results demonstrate the framework's superior performance, confirming its effectiveness in real-world scenarios.
  arXiv  Detail & Related papers  (2024-08-05T06:31:39Z)
• MobileExperts: A Dynamic Tool-Enabled Agent Team in Mobile Devices [17.702068044185086]
  This paper introduces MobileExperts, which for the first time introduces tool formulation and multi-agent collaboration. We develop a dual-layer planning mechanism to establish coordinate collaboration among experts. Experimental results demonstrate that MobileExperts performs better on all intelligence levels and achieves 22% reduction in reasoning costs.
  arXiv  Detail & Related papers  (2024-07-04T13:12:19Z)
• Mobile-Agent-v2: Mobile Device Operation Assistant with Effective Navigation via Multi-Agent Collaboration [52.25473993987409]
  We propose Mobile-Agent-v2, a multi-agent architecture for mobile device operation assistance. The architecture comprises three agents: planning agent, decision agent, and reflection agent. We show that Mobile-Agent-v2 achieves over a 30% improvement in task completion compared to the single-agent architecture.
  arXiv  Detail & Related papers  (2024-06-03T05:50:00Z)
• Benchmarking Mobile Device Control Agents across Diverse Configurations [19.01954948183538]
  B-MoCA is a benchmark for evaluating and developing mobile device control agents. We benchmark diverse agents, including agents employing large language models (LLMs) or multi-modal LLMs. While these agents demonstrate proficiency in executing straightforward tasks, their poor performance on complex tasks highlights significant opportunities for future research to improve effectiveness.
  arXiv  Detail & Related papers  (2024-04-25T14:56:32Z)
• MEIA: Multimodal Embodied Perception and Interaction in Unknown Environments [82.67236400004826]
  We introduce the Multimodal Embodied Interactive Agent (MEIA), capable of translating high-level tasks expressed in natural language into a sequence of executable actions. MEM module enables MEIA to generate executable action plans based on diverse requirements and the robot's capabilities.
  arXiv  Detail & Related papers  (2024-02-01T02:43:20Z)
• Mobile-Agent: Autonomous Multi-Modal Mobile Device Agent with Visual Perception [52.5831204440714]
  We introduce Mobile-Agent, an autonomous multi-modal mobile device agent. Mobile-Agent first leverages visual perception tools to accurately identify and locate both the visual and textual elements within the app's front-end interface. It then autonomously plans and decomposes the complex operation task, and navigates the mobile Apps through operations step by step.
  arXiv  Detail & Related papers  (2024-01-29T13:46:37Z)
• MobileAgent: enhancing mobile control via human-machine interaction and SOP integration [0.0]
  Large Language Models (LLMs) are now capable of automating mobile device operations for users. Privacy concerns related to personalized user data arise during mobile operations, requiring user confirmation. We have designed interactive tasks between agents and humans to identify sensitive information and align with personalized user needs. Our approach is evaluated on the new device control benchmark AitW, which encompasses 30K unique instructions across multi-step tasks.
  arXiv  Detail & Related papers  (2024-01-04T03:44:42Z)
• TaskBench: Benchmarking Large Language Models for Task Automation [82.2932794189585]
  We introduce TaskBench, a framework to evaluate the capability of large language models (LLMs) in task automation. Specifically, task decomposition, tool selection, and parameter prediction are assessed. Our approach combines automated construction with rigorous human verification, ensuring high consistency with human evaluation.
  arXiv  Detail & Related papers  (2023-11-30T18:02:44Z)
• MoConVQ: Unified Physics-Based Motion Control via Scalable Discrete Representations [25.630268570049708]
  MoConVQ is a novel unified framework for physics-based motion control leveraging scalable discrete representations. Our approach effectively learns motion embeddings from a large, unstructured dataset spanning tens of hours of motion examples.
  arXiv  Detail & Related papers  (2023-10-16T09:09:02Z)
• Plan, Eliminate, and Track -- Language Models are Good Teachers for Embodied Agents [99.17668730578586]
  Pre-trained large language models (LLMs) capture procedural knowledge about the world. Plan, Eliminate, and Track (PET) framework translates a task description into a list of high-level sub-tasks. PET framework leads to a significant 15% improvement over SOTA for generalization to human goal specifications.
  arXiv  Detail & Related papers  (2023-05-03T20:11:22Z)
• Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion [68.45737688496654]
  We present a modular interactive VOS framework which decouples interaction-to-mask and mask propagation. We show that our method outperforms current state-of-the-art algorithms while requiring fewer frame interactions.
  arXiv  Detail & Related papers  (2021-03-14T14:39:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.