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

arXiv: https://arxiv.org/abs/2607.00502 · HTML: https://mlsanity.com/paper/2607.00502/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in GUI and mobile agents, one of 16 directions in LLM agents and tool use.
- Builds on 11 of its 19 references that are in the map.
- First posted on arXiv 1 Jul 2026.

## Placed in

- LLM agents and tool use / [GUI and mobile agents](https://mlsanity.com/agents/gui-and-mobile-agents/)

## Builds on (most cited first, 11 of 11)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Kimi K2.5: Visual Agentic Intelligence](https://mlsanity.com/paper/2602.02276/) (2026)
- [MobileWorld: Benchmarking Autonomous Mobile Agents in Agent-User Interactive and MCP-Augmented Environments](https://mlsanity.com/paper/2512.19432/) (2025)
- [Scaling LLM Multi-turn RL with End-to-end Summarization-based Context Management](https://mlsanity.com/paper/2510.06727/) (2025)
- [IterResearch: Rethinking Long-Horizon Agents with Interaction Scaling](https://mlsanity.com/paper/2511.07327/) (2025)
- [MemGUI-Bench: Benchmarking Memory of Mobile GUI Agents in Dynamic Environments](https://mlsanity.com/paper/2602.06075/) (2026)
- [PAL-UI: Planning with Active Look-back for Vision-Based GUI Agents](https://mlsanity.com/paper/2510.00413/) (2025)
- [VenusBench-Mobile: A Challenging and User-Centric Benchmark for Mobile GUI Agents with Capability Diagnostics](https://mlsanity.com/paper/2604.06182/) (2026)
- [UI-Copilot: Advancing Long-Horizon GUI Automation via Tool-Integrated Policy Optimization](https://mlsanity.com/paper/2604.13822/) (2026)
- [Where and How to Prune: An Empirical Study of Visual Token Pruning for GUI Agent Navigation](https://mlsanity.com/paper/2603.26041/) (2026)

## Built on by (most cited first, 2 of 2)

- [StepReflect: Structured UI Transition Reflection for Mobile GUI Agents](https://mlsanity.com/paper/2608.05587/) (2026)
- [Benchmarking General Mobile Assistants in Challenging Real-World Scenarios](https://mlsanity.com/paper/2608.27477/) (2026)

## Abstract (arXiv)

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.