AI Agents for Computer Use: A Review of Instruction-based Computer Control, GUI Automation, and Operator Assistants
- URL: http://arxiv.org/abs/2501.16150v1
- Date: Mon, 27 Jan 2025 15:44:02 GMT
- Title: AI Agents for Computer Use: A Review of Instruction-based Computer Control, GUI Automation, and Operator Assistants
- Authors: Pascal J. Sager, Benjamin Meyer, Peng Yan, Rebekka von Wartburg-Kottler, Layan Etaiwi, Aref Enayati, Gabriel Nobel, Ahmed Abdulkadir, Benjamin F. Grewe, Thilo Stadelmann,
- Abstract summary: This review offers a comprehensive overview of the emerging field of instruction-based computer control.<n>We formalize the problem and establish a taxonomy of the field to analyze agents from three perspectives.<n>In total, we review and classify 86 CCAs and 33 related datasets.
- Score: 4.904229981437243
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Instruction-based computer control agents (CCAs) execute complex action sequences on personal computers or mobile devices to fulfill tasks using the same graphical user interfaces as a human user would, provided instructions in natural language. This review offers a comprehensive overview of the emerging field of instruction-based computer control, examining available agents -- their taxonomy, development, and respective resources -- and emphasizing the shift from manually designed, specialized agents to leveraging foundation models such as large language models (LLMs) and vision-language models (VLMs). We formalize the problem and establish a taxonomy of the field to analyze agents from three perspectives: (a) the environment perspective, analyzing computer environments; (b) the interaction perspective, describing observations spaces (e.g., screenshots, HTML) and action spaces (e.g., mouse and keyboard actions, executable code); and (c) the agent perspective, focusing on the core principle of how an agent acts and learns to act. Our framework encompasses both specialized and foundation agents, facilitating their comparative analysis and revealing how prior solutions in specialized agents, such as an environment learning step, can guide the development of more capable foundation agents. Additionally, we review current CCA datasets and CCA evaluation methods and outline the challenges to deploying such agents in a productive setting. In total, we review and classify 86 CCAs and 33 related datasets. By highlighting trends, limitations, and future research directions, this work presents a comprehensive foundation to obtain a broad understanding of the field and push its future development.
Related papers
- OS Agents: A Survey on MLLM-based Agents for General Computing Devices Use [101.57043903478257]
The dream to create AI assistants as capable and versatile as the fictional J.A.R.V.I.S from Iron Man has long captivated imaginations.<n>With the evolution of (multi-modal) large language models ((M)LLMs), this dream is closer to reality.<n>This survey aims to consolidate the state of OS Agents research, providing insights to guide both academic inquiry and industrial development.
arXiv Detail & Related papers (2025-08-06T14:33:45Z) - Generic-to-Specific Reasoning and Learning for Scalable Ad Hoc Teamwork [10.462598319732187]
This paper advocates leveraging the complementary strengths of knowledge-based and data-driven methods for reasoning and learning for ad hoc teamwork.<n>For any given goal, our architecture enables each ad hoc agent to determine its actions through non-monotonic logical reasoning.<n>We experimentally evaluate our architecture's capabilities in VirtualHome, a realistic physics-based 3D simulation environment.
arXiv Detail & Related papers (2025-08-06T07:44:38Z) - A Survey of Self-Evolving Agents: On Path to Artificial Super Intelligence [87.08051686357206]
Large Language Models (LLMs) have demonstrated strong capabilities but remain fundamentally static.<n>As LLMs are increasingly deployed in open-ended, interactive environments, this static nature has become a critical bottleneck.<n>This survey provides the first systematic and comprehensive review of self-evolving agents.
arXiv Detail & Related papers (2025-07-28T17:59:05Z) - OS-MAP: How Far Can Computer-Using Agents Go in Breadth and Depth? [30.788287791669458]
OS-MAP is a benchmark for daily computer-using automation.<n>It organizes its 416 realistic tasks across 15 applications along two key dimensions.<n>It captures varying levels of required agent autonomy and generalization.
arXiv Detail & Related papers (2025-07-25T10:14:53Z) - Understanding Software Engineering Agents: A Study of Thought-Action-Result Trajectories [18.129031749321058]
Large Language Model (LLM)-based agents are increasingly employed to automate complex software engineering tasks.<n>Despite their widespread adoption, the internal decision-making processes of these agents remain largely unexplored.<n>We present a large-scale empirical study of the thought-action-result trajectories of three state-of-the-art LLM-based agents.
arXiv Detail & Related papers (2025-06-23T16:34:52Z) - Deep Research Agents: A Systematic Examination And Roadmap [79.04813794804377]
Deep Research (DR) agents are designed to tackle complex, multi-turn informational research tasks.<n>In this paper, we conduct a detailed analysis of the foundational technologies and architectural components that constitute DR agents.
arXiv Detail & Related papers (2025-06-22T16:52:48Z) - Towards Pervasive Distributed Agentic Generative AI -- A State of The Art [0.0]
The rapid advancement of intelligent agents and Large Language Models (LLMs) is reshaping the pervasive computing field.<n>This survey outlines the architectural components of LLM agents and examines their deployment and evaluation across various scenarios.<n>It highlights state-of-the-art agent deployment strategies and applications, including local and distributed execution on resource-constrained devices.
arXiv Detail & Related papers (2025-06-16T10:15:06Z) - Unifying Language Agent Algorithms with Graph-based Orchestration Engine for Reproducible Agent Research [32.92036657863354]
Language agents powered by large language models (LLMs) have demonstrated remarkable capabilities in understanding, reasoning, and executing complex tasks.<n>However, developing robust agents presents significant challenges: substantial engineering overhead, lack of standardized components, and insufficient evaluation frameworks for fair comparison.<n>We introduce Agent Graph-based Orchestration for Reasoning and Assessment (AGORA), a flexible and abstraction framework that addresses these challenges.
arXiv Detail & Related papers (2025-05-30T08:46:23Z) - ThinkGeo: Evaluating Tool-Augmented Agents for Remote Sensing Tasks [54.52092001110694]
ThinkGeo is a benchmark designed to evaluate tool-augmented agents on remote sensing tasks via structured tool use and multi-step planning.<n>Inspired by tool-interaction paradigms, ThinkGeo includes human-curated queries spanning a wide range of real-world applications.<n>Our analysis reveals notable disparities in tool accuracy and planning consistency across models.
arXiv Detail & Related papers (2025-05-29T17:59:38Z) - A Desideratum for Conversational Agents: Capabilities, Challenges, and Future Directions [51.96890647837277]
Large Language Models (LLMs) have propelled conversational AI from traditional dialogue systems into sophisticated agents capable of autonomous actions, contextual awareness, and multi-turn interactions with users.
This survey paper presents a desideratum for next-generation Conversational Agents - what has been achieved, what challenges persist, and what must be done for more scalable systems that approach human-level intelligence.
arXiv Detail & Related papers (2025-04-07T21:01:25Z) - A Survey on (M)LLM-Based GUI Agents [62.57899977018417]
Graphical User Interface (GUI) Agents have emerged as a transformative paradigm in human-computer interaction.
Recent advances in large language models and multimodal learning have revolutionized GUI automation across desktop, mobile, and web platforms.
This survey identifies key technical challenges, including accurate element localization, effective knowledge retrieval, long-horizon planning, and safety-aware execution control.
arXiv Detail & Related papers (2025-03-27T17:58:31Z) - Large Language Model Agent: A Survey on Methodology, Applications and Challenges [88.3032929492409]
Large Language Model (LLM) agents, with goal-driven behaviors and dynamic adaptation capabilities, potentially represent a critical pathway toward artificial general intelligence.
This survey systematically deconstructs LLM agent systems through a methodology-centered taxonomy.
Our work provides a unified architectural perspective, examining how agents are constructed, how they collaborate, and how they evolve over time.
arXiv Detail & Related papers (2025-03-27T12:50:17Z) - AIOpsLab: A Holistic Framework to Evaluate AI Agents for Enabling Autonomous Clouds [12.464941027105306]
AI for IT Operations (AIOps) aims to automate complex operational tasks, such as fault localization and root cause analysis, to reduce human workload and minimize customer impact.<n>Recent advances in Large Language Models (LLMs) and AI agents are revolutionizing AIOps by enabling end-to-end and multitask automation.<n>We present AIOPSLAB, a framework that deploys microservice cloud environments, injects faults, generates workloads, and exports telemetry data but also orchestrates these components and provides interfaces for interacting with and evaluating agents.
arXiv Detail & Related papers (2025-01-12T04:17:39Z) - GUI Agents: A Survey [129.94551809688377]
Graphical User Interface (GUI) agents, powered by Large Foundation Models, have emerged as a transformative approach to automating human-computer interaction.<n>Motivated by the growing interest and fundamental importance of GUI agents, we provide a comprehensive survey that categorizes their benchmarks, evaluation metrics, architectures, and training methods.
arXiv Detail & Related papers (2024-12-18T04:48:28Z) - GUI Agents with Foundation Models: A Comprehensive Survey [52.991688542729385]
This survey consolidates recent research on (M)LLM-based GUI agents.
We highlight key innovations in data, frameworks, and applications.
We hope this paper will inspire further developments in the field of (M)LLM-based GUI agents.
arXiv Detail & Related papers (2024-11-07T17:28:10Z) - Agent S: An Open Agentic Framework that Uses Computers Like a Human [31.16046798529319]
We present Agent S, an open agentic framework that enables autonomous interaction with computers through a Graphical User Interface (GUI)
Agent S aims to address three key challenges in automating computer tasks: acquiring domain-specific knowledge, planning over long task horizons, and handling dynamic, non-uniform interfaces.
arXiv Detail & Related papers (2024-10-10T17:43:51Z) - Data Analysis in the Era of Generative AI [56.44807642944589]
This paper explores the potential of AI-powered tools to reshape data analysis, focusing on design considerations and challenges.
We explore how the emergence of large language and multimodal models offers new opportunities to enhance various stages of data analysis workflow.
We then examine human-centered design principles that facilitate intuitive interactions, build user trust, and streamline the AI-assisted analysis workflow across multiple apps.
arXiv Detail & Related papers (2024-09-27T06:31:03Z) - AgentStudio: A Toolkit for Building General Virtual Agents [57.02375267926862]
General virtual agents need to handle multimodal observations, master complex action spaces, and self-improve in dynamic, open-domain environments.
AgentStudio provides a lightweight, interactive environment with highly generic observation and action spaces.
It integrates tools for creating online benchmark tasks, annotating GUI elements, and labeling actions in videos.
Based on our environment and tools, we curate an online task suite that benchmarks both GUI interactions and function calling with efficient auto-evaluation.
arXiv Detail & Related papers (2024-03-26T17:54:15Z) - Knowledge-based Reasoning and Learning under Partial Observability in Ad
Hoc Teamwork [4.454557728745761]
This paper introduces an architecture that determines an ad hoc agent's behavior based on non-monotonic logical reasoning.
It supports online selection, adaptation, and learning of the models that predict the other agents' behavior.
We show that the performance of our architecture is comparable or better than state of the art data-driven baselines in both simple and complex scenarios.
arXiv Detail & Related papers (2023-06-01T15:21:27Z) - Toward a Reasoning and Learning Architecture for Ad Hoc Teamwork [4.454557728745761]
We present an architecture for ad hoc teamwork, which refers to collaboration in a team of agents without prior coordination.
Our architecture combines the principles of knowledge-based and data-driven reasoning and learning.
We use the benchmark simulated multiagent collaboration domain Fort Attack to demonstrate that our architecture supports adaptation to unforeseen changes.
arXiv Detail & Related papers (2022-08-24T13:57:33Z) - Realistic simulation of users for IT systems in cyber ranges [63.20765930558542]
We instrument each machine by means of an external agent to generate user activity.
This agent combines both deterministic and deep learning based methods to adapt to different environment.
We also propose conditional text generation models to facilitate the creation of conversations and documents.
arXiv Detail & Related papers (2021-11-23T10:53:29Z)
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.