A Task-State Representation for Long-Horizon Mobile GUI Agents

• URL: http://arxiv.org/abs/2607.00502v1
• Date: Wed, 01 Jul 2026 06:37:21 GMT
• Title: A Task-State Representation for Long-Horizon Mobile GUI Agents
• Abstract summary: Task-State Representation (TSR) is a training-free framework that explicitly decouples task state from sensory input.<n> Experiments across four mobile GUI benchmarks validate TSR's effectiveness, yielding up to a 12 absolute point increase in success rate.
• Score: 53.359524744953575
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: While long-horizon mobile GUI agents typically rely on thought-action-observation loops, they struggle to separate persistent task states from transient screen observations. As execution histories grow, this entanglement imposes a severe context burden, causing agents to forget initial requirements, hallucinate progress, or repeatedly interact with stale interfaces. To address this, we introduce Task-State Representation (TSR), a training-free framework that explicitly decouples task state from sensory input. Acting as a lightweight external wrapper, TSR maintains three structured components: a global instruction summary, a dynamic progress tracker for subgoals, and a transition-aware action verifier. By continuously updating through pre- and post-action visual comparisons, TSR effectively guides the agent's reasoning without requiring architectural modifications. Experiments across four mobile GUI benchmarks validate TSR's effectiveness, yielding up to a 12 absolute point increase in success rate on complex cross-application and memory-intensive tasks.

Related papers

• Compiling and Benchmarking Task-State Horizons for Embodied Agents [2.8397380902242966]
  Frontier agentic models are increasingly deployed as high-level planners for long-horizon embodied tasks.<n>We define the span of task-relevant state transitions that an agent must track as task-state horizon (TSH)<n>We introduce RoboGraph, a robotic task compiler that translates state-transition dependencies into executable symbolic graphs.
  arXiv  Detail & Related papers  (2026-08-08T09:45:01Z)
• STAMP: Training Explicit Memory for Mobile GUI Agents in Controllable and Scalable Virtual Environments [63.39393178045112]
  Mobile agents excel at immediate reactive control but frequently fail in realistic, longhorizon tasks that require memory.<n>We present STAMP, a framework that trains explicit memory in mobile agents through controllable virtual environments.<n>The resulting StampGUI agent sets a new high watermark on our Memory-World benchmark, demonstrating exceptional memory accuracy and task resilience.
  arXiv  Detail & Related papers  (2026-05-28T04:00:13Z)
• GTA: Generating Long-Horizon Tasks for Web Agents at Scale [82.43869456830664]
  We introduce a scalable framework, GTA, that integrates crawling, retrieval-based seeding, in-context generation, and automated quality control.<n>We instantiate the pipeline on over 50 websites covering e-commerce, government, forums, and news, with multilingual and multi-hop coverage.<n>Our contributions are three-fold: (i) formalizing multi-hop web-agent task generation, (ii) proposing an efficient and validated pipeline for automatic data creation, and (iii) releasing a dynamic benchmark with reproducible evaluation.
  arXiv  Detail & Related papers  (2026-05-28T01:05:50Z)
• PIRA-Bench: A Transition from Reactive GUI Agents to GUI-based Proactive Intent Recommendation Agents [32.98769345205729]
  PIRA-Bench is a novel benchmark for evaluating multimodal large language models (MLLMs) on continuous, weakly-supervised visual inputs.<n>We propose the PIRF baseline, a memory-aware, state-tracking framework that empowers general MLLMs to manage multiple task threads and handle misleading visual inputs.
  arXiv  Detail & Related papers  (2026-03-09T06:41:32Z)
• ANCHOR: Branch-Point Data Generation for GUI Agents [52.22377425487]
  End-to-end GUI agents for real desktop environments require large amounts of high-quality interaction data.<n>We present a trajectory expansion framework Anchor that bootstraps scalable desktop supervision from a small set of verified seed demonstrations.<n>Experiments on standard desktop benchmarks, OSWorld and WindowsAgentArena, show that models fine-tuned on our expanded corpus achieve consistent improvements.
  arXiv  Detail & Related papers  (2026-02-06T19:55:26Z)
• AgentProg: Empowering Long-Horizon GUI Agents with Program-Guided Context Management [24.465443389008055]
  AgentProg is a program-guided approach for agent context management.<n>It reframes the interaction history as a program with variables and control flow.<n> Experiments on AndroidWorld and our extended long-horizon task suite demonstrate that AgentProg has achieved the state-of-the-art success rates.
  arXiv  Detail & Related papers  (2025-12-11T07:37:38Z)
• GUI-PRA: Process Reward Agent for GUI Tasks [25.20594694997543]
  Process Reward Models (PRMs) are a promising solution, as they can guide these agents with crucial process signals during inference.<n>PRMs suffer from a "lost in the middle" phenomenon, where the overwhelming historical context compromises the evaluation of the current step.<n>We introduce GUI-PRA (Process Reward Agent for GUI Tasks), a judge agent designed to better provide process reward than standard PRM.
  arXiv  Detail & Related papers  (2025-09-27T11:42:36Z)
• MAPLE: A Mobile Agent with Persistent Finite State Machines for Structured Task Reasoning [46.18718721121415]
  We present MAPLE, a state-aware multi-agent framework that abstracts app interactions as a Finite State Machine (FSM)<n>We computationally model each UI screen as a discrete state and user actions as transitions, allowing the FSM to provide a structured representation of the app execution.<n> MAPLE consists of specialized agents responsible for four phases of task execution: planning, execution, verification, error recovery, and knowledge retention.
  arXiv  Detail & Related papers  (2025-05-29T16:08:51Z)
• DriveTransformer: Unified Transformer for Scalable End-to-End Autonomous Driving [62.62464518137153]
  DriveTransformer is a simplified E2E-AD framework for the ease of scaling up.<n>It is composed of three unified operations: task self-attention, sensor cross-attention, temporal cross-attention.<n>It achieves state-of-the-art performance in both simulated closed-loop benchmark Bench2Drive and real world open-loop benchmark nuScenes with high FPS.
  arXiv  Detail & Related papers  (2025-03-07T11:41:18Z)
• 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.<n>Mobile-Agent-E achieves a 22% absolute improvement over previous state-of-the-art approaches.
  arXiv  Detail & Related papers  (2025-01-20T20:35:46Z)

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.