提出本地部署的GUI代理控制架构，提升长期任务执行稳定性。
LocalLSTC: A Long Short-Term Control Architecture for Locally Deployed GUI Agents
- 按时间范围分层管理控制信息，长程保持目标与反馈，短程专注当前动作。
- 在Qwen3.6-27B下，OSWorld SR-100达64.7%，WindowsAgentArena达65.3%。
- 无需训练，适用于资源受限场景，适合构建可靠本地智能助手。
现代GUI代理框架虽借助前沿大模型实现优秀桌面任务表现，但控制信息常隐含于不断增长的交互轨迹中。每一步规划器需重新推断任务阶段、累积证据和运行反馈以决定下一步行动，这一依赖在本地推理能力较弱时尤为显著。在四个主流框架中，将GPT-5替换为Qwen3.5-9B后，OSWorld SR-100从60.9%降至37.7%。轨迹标注显示，91.6%的失败轨迹至少存在一次控制失效。为此，我们提出LocalLSTC——一种无需训练的架构，通过时间维度组织控制信息：长程控制维护活跃子目标、对齐证据与运行反馈，短程执行则聚焦当前步骤的有限承诺。长到短规划基于持久状态生成动作，短到长控制将执行结果回传至状态以评估进展、恢复或终止。使用Qwen3.6-27B时，LocalLSTC在OSWorld上达到64.7% SR-100，WindowsAgentArena上达65.3%，优于所有先前本地基线。消融实验验证了两端机制的贡献。研究揭示，控制信息的时间组织是本地部署GUI代理的关键架构维度。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。