{"ID":5551874,"CreatedAt":"2026-07-02T01:54:51.863792489Z","UpdatedAt":"2026-07-04T06:25:51.571775532Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.00502","arxiv_id":"2607.00502","title":"A Task-State Representation for Long-Horizon Mobile GUI Agents","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.","short_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 progres...","url_abs":"https://arxiv.org/abs/2607.00502","url_pdf":"https://arxiv.org/pdf/2607.00502v1","authors":"[\"Yujie Zheng\",\"Zikang Liu\",\"Xin Zhao\",\"Ji-Rong Wen\"]","published":"2026-07-01T06:37:21Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[]","has_code":false}