LocalLSTC: A Long Short-Term Control Architecture for Locally Deployed GUI Agents

• URL: http://arxiv.org/abs/2608.25777v1
• Date: Wed, 26 Aug 2026 13:20:27 GMT
• Title: LocalLSTC: A Long Short-Term Control Architecture for Locally Deployed GUI Agents
• Abstract summary: We introduce LocalLSTC, a training-free architecture that organizes control by temporal scope, maintaining persistent cross-step state.<n>Long-Term Control maintains the active subgoal, subgoal-aligned evidence, and runtime feedback across interactions, while Short-Term Execution realizes bounded commitments for the current step.<n>With Qwen3.6-27B, LocalLSTC reaches 64.7% SR-100 on OSWorld and 65.3% on WindowsAgentArena, outperforming the strongest prior local results on both benchmarks.
• Score: 13.261859864631063
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Modern GUI-agent frameworks achieve strong desktop task performance with frontier API models, yet persistent control information often remains implicit in growing interaction trajectories. At each step, the planner reconstructs the active task stage, accumulated evidence, and runtime feedback before deciding the next action. This dependence becomes more pronounced under weaker local reasoning backbones. Across four representative state-of-the-art frameworks, replacing GPT-5 with Qwen3.5-9B reduces average OSWorld SR-100 from 60.9\% to 37.7\%. Trajectory annotation further identifies at least one control failure in 91.6\% of failed trajectories. To address this problem, we introduce LocalLSTC, a training-free architecture that organizes control by temporal scope, maintaining persistent cross-step state to guide short-term execution commitments. Long-Term Control maintains the active subgoal, subgoal-aligned evidence, and runtime feedback across interactions, while Short-Term Execution realizes bounded commitments for the current step. Long-to-Short Planning forms each commitment from persistent state, and Short-to-Long Control integrates execution outcomes back into that state for progress assessment, recovery, and termination. With Qwen3.6-27B, LocalLSTC reaches 64.7\% SR-100 on OSWorld and 65.3\% on WindowsAgentArena, outperforming the strongest prior local results on both benchmarks. Ablations further support contributions from mechanisms on both sides of execution. These findings identify temporal organization of control information as a distinct architectural dimension for locally deployed GUI agents.

Related papers

• StructAgent: Harness Long-horizon Digital Agents with Unified Causal Structure [29.25570731801935]
  StructAgent is a state-centered framework for maintaining compact, verifiable task progress.<n>It enables explicit progress checkpointing, evidence-driven task completion, targeted failure recovery, and tool-supported execution.<n>It generalizes beyond desktop environments to Minecraft, demonstrating the generality of our design.
  arXiv  Detail & Related papers  (2026-07-13T10:48:25Z)
• A Formal Hierarchical Architecture for Agentic Orchestration with Stack-Based Execution and Lazy Discovery [5.106901034158075]
  This paper presents a hierarchical, skill-based architecture for agentic orchestration.<n> Capabilities are organized as a rooted tree where internal nodes make routing decisions and leaf nodes execute deterministic tasks.<n>By replacing global memory with localized stack frames, the architecture prevents outputs from one execution branch from leaking into another.
  arXiv  Detail & Related papers  (2026-07-13T06:15:51Z)
• A Task-State Representation for Long-Horizon Mobile GUI Agents [53.359524744953575]
  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.
  arXiv  Detail & Related papers  (2026-07-01T06:37:21Z)
• StainFlow: Entity-Stain Tracking and Evidence Linking for Process Rewards in GUI Agents [67.03593791535786]
  Reinforcement Learning (RL) has become a promising approach for improving GUI Agents in long-horizon, digital environments.<n>To mitigate this issue, recent studies introduce Process Reward Models (PRMs)<n>PRMs provide finer-grained training feedback through global milestone verification or local step-level evaluation.<n>We propose StainFlow, an entity-stain-flow process reward model for GUI Agents.
  arXiv  Detail & Related papers  (2026-06-05T08:17:28Z)
• Beyond Semantic Organization: Memory as Execution State Management for Long-Horizon Agents [18.30583250316923]
  LLM-based agents increasingly tackle long-horizon tasks with interdependent decisions.<n>Existing RAG and agent memory systems organize histories by semantic similarity, retrieving content-relevant entries at decision time.<n>We propose MAGE (Memory as Agent-Guided Exploration), an active execution-state manager that stores interactions in a hierarchical state tree.
  arXiv  Detail & Related papers  (2026-06-04T12:26:42Z)
• ClawForge: Generating Executable Interactive Benchmarks for Command-Line Agents [59.626170560327274]
  We present textbfClawForge, a generator-backed benchmark framework for executable command-line categories under state conflict.<n>We instantiate this framework as the ClawForge-Bench (17 scenarios, 6 ability categories)
  arXiv  Detail & Related papers  (2026-05-13T21:34:08Z)
• Step-level Optimization for Efficient Computer-use Agents [51.29573359027217]
  We argue that strong computer-use agents remain expensive and slow in practice.<n>We propose an event-driven, step-level cascade for computer-use agents.
  arXiv  Detail & Related papers  (2026-04-29T19:59:36Z)
• AsyncVLA: An Asynchronous VLA for Fast and Robust Navigation on the Edge [49.66156306240961]
  High latency breaks the control loop, rendering powerful models unsafe for real-time deployment.<n>We propose AsyncVLA, an asynchronous control framework that decouples semantic reasoning from reactive execution.<n>AsyncVLA achieves a 40% higher success rate than state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-02-13T21:31:19Z)
• 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)

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.