SOURCE-LINKED INTELLIGENCE

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

arXiv · AI, language, vision and robotics · article · Aug 26, 2026 · UTC

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 o

Read original source ↗ Open in workspace

recordType

paper

region

Global