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

arXiv:2608.25777 · cs.AI · Submitted 2026-08-26 · Read on arXiv

cs.AI

Submitted: 2026-08-26

Updated: 2026-09-25

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Verification — 38× in this paper · explained in 2 episodes
• Abstraction — 20× in this paper · explained in 1 episode
• Step Abstraction — 17× in this paper
• Benchmark — 16× in this paper · explained in 2 episodes
• Ablation — 10× in this paper · explained in 1 episode
• Grounding — 7× in this paper · explained in 3 episodes
• Adaptation — 3× in this paper · explained in 1 episode
• Fine-Tuning — 3× in this paper · explained in 5 episodes
• Verifier — 3× in this paper · explained in 2 episodes
• Action Space — 2× in this paper · explained in 1 episode
• Annotator Agreement — 2× in this paper · explained in 1 episode
• Benchmarking — 2× in this paper · explained in 3 episodes
• Long Short Term Control — 2× in this paper
• Reinforcement Learning — 2× in this paper · explained in 4 episodes
• Trace — 2× in this paper · explained in 2 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Adam — 1× in this paper · explained in 2 episodes
• Agentic Framework — 1× in this paper · explained in 6 episodes
• Aggregation — 1× in this paper · explained in 1 episode
• Consistency — 1× in this paper · explained in 3 episodes
• Core — 1× in this paper · explained in 2 episodes
• F1 Score — 1× in this paper · explained in 3 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Fingerprinting — 1× in this paper · explained in 2 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Online Reinforcement Learning — 1× in this paper · explained in 2 episodes
• Reconstruction Error — 1× in this paper · explained in 2 episodes
• Steering — 1× in this paper · explained in 2 episodes
• Test-time Scaling — 1× in this paper · explained in 2 episodes
• Unified Framework — 1× in this paper · explained in 5 episodes

Sources

• Qwen2.5-VL Technical Report
• UI-CUBE: Enterprise-Grade Computer Use Agent Benchmarking Beyond Task Accuracy to Operational Reliability
• Kimi-VL Technical Report
• Mano Technical Report
• Scaling Agents for Computer Use
• Seed1.5-VL Technical Report
• Agentic Lybic: Multi-Agent Execution System with Tiered Reasoning and Orchestration
• VLAA-GUI: Knowing When to Stop, Recover, and Search, A Modular Framework for GUI Automation
• Avenir-Web: Human-Experience-Imitating Multimodal Web Agents with Mixture of Grounding Experts
• UI-TARS: Pioneering Automated GUI Interaction with Native Agents
• ClawGUI: A Unified Framework for Training, Evaluating, and Deploying GUI Agents
• Plover: Steering GUI Agents through Plan-Centric Interaction
• UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning
• A Subgoal-driven Framework for Improving Long-Horizon LLM Agents
• InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
• Mobile-Agent-v3.5: Multi-platform Fundamental GUI Agents
• Adapting the Interface, Not the Model: Runtime Harness Adaptation for Deterministic LLM Agents
• EvoCUA: Evolving Computer Use Agents via Learning from Scalable Synthetic Experience
• PowerInfer-2: Fast Large Language Model Inference on a Smartphone

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection