Browse 19 reviewed surveys connected to computer-use, GUI, web, and mobile agents. Each entry links to primary evidence and records its scope.
Review means AI-assisted editorial inspection, not independent reproduction. Unknown licenses and specifications remain unknown.
Reviews 87 computer-use agents and 33 datasets through a taxonomy of operating domain, observation and action modalities, and agent design.
2025-01-27 · cross-platformSurveys foundation-model web agents through their architectures, training methods and trustworthiness. It organizes research on completing browser tasks from user instructions and identifies directions for further development.
2025-03-30 · webAnalyzes LLM-based GUI agents through four components (perception, exploration, planning, and interaction) and the methods used to evaluate them.
2025-03-27 · cross-platformFormalizes GUI tasks as Markov decision processes and traces agent training from prompting through supervised fine-tuning to reinforcement learning.
2025-04-29 · cross-platformOrganizes security risks and defenses for persistent agent memory into six lifecycle phases and proposes five verifiable governance primitives.
2026-04-17 · unspecifiedSystematizes safety and security threats to computer-using agents, with taxonomies of threats and defensive strategies.
2025-05-16 · cross-platformSurveys modular agentic skill architectures, skill lifecycles, and security risks in autonomous tool- and interface-using agents.
2026-08-30 · cross-platformPresents a conceptual perception–reasoning–action framework and 12 potential attack scenarios for language agents, including hypothetical web-navigation attacks.
2024-02-15 · webThis survey organizes agent skills by architecture, acquisition, deployment and security, including their role in computer-use systems and GUI grounding. It also proposes a permission and lifecycle governance framework for skill deployment.
2026-02-12 · unspecifiedSurveys GUI-agent efficiency beyond task success: observation, context and memory, action, and planner or runtime cost.
2026-09-02 · cross-platformSurveys multimodal mobile agents, organizing prompt-based and training-based approaches alongside evaluation benchmarks, supporting technologies, and open challenges in mobile task execution.
2024-11-04 · unspecifiedSurveys virtual agents for browsers, applications and operating systems, organizing prior work by task type, observation and action spaces, model strategies and evaluation methods. It examines screen-based interaction and keyboard, mouse and touch control, alongside transferability and long-sequence decision-making challenges.
2024-11-17 · web, desktop, android, windowsSurvey of (M)LLM-based GUI agents organized around their datasets and benchmarks, a unified agent framework with a taxonomy, and commercial applications.
2024-11-07 · cross-platformCategorizes GUI-agent benchmarks, evaluation metrics, architectures, and training methods, and proposes a unified perception, reasoning, planning, and acting framework.
2024-12-18 · cross-platformSurvey of LLM-brained GUI agents that carry out natural-language instructions across web, mobile, and desktop interfaces, organizing research and industry progress.
2024-11-27 · cross-platformReviews LLM-driven phone GUI agents with a taxonomy of agent frameworks, prompt- and training-based modeling, datasets, and benchmarks.
2025-04-28 · android, iosSurveys agents that operate computers and phones through operating-system interfaces, covering components, capabilities, foundation models, frameworks, and benchmarks.
2025-08-06 · cross-platformSurveys multimodal memory using representation and management axes, distinguishing fixed-policy updates from policy evolution and comparing GUI memory evaluation with other modalities.
2026-10-14 · unspecifiedFrames GUI-agent trustworthiness as an execution gap and reviews failures, attacks, and defenses across perception, reasoning, and interaction.
2025-03-30 · cross-platform