When to Compile a Computer-Use Agent? Measuring Payback and Making Compilation Decisions for Token Efficiency
cs.AI
Submitted: 2026-10-02
Updated: 2026-10-02
Code: https://github.com/myl7/computer-
Sources
- AutoRPA: Efficient GUI Automation through LLM-Driven Code Synthesis from Interactions
- D-GARA: A Dynamic Benchmarking Framework for GUI Agent Robustness in Real-World Anomalies
- TraceCompiler: Skill-Guided Mining and Compilation of LLM Agent Traces into Mostly Deterministic Workflows
- CogAgent: A Visual Language Model for GUI Agents
- Conservative Contextual Linear Bandits
- Benchmarking Mobile Device Control Agents across Diverse Configurations
- PreAct: Computer-Using Agents that Get Faster on Repeated Tasks
- Beyond Static Endpoints: Tool Programs as an Interface for Flexible Agentic Web Services
- AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents
- Compiled AI: Deterministic Code Generation for LLM-Based Workflow Automation
- OpenApps: Simulating Environment Variations to Measure UI-Agent Reliability
- Inducing Programmatic Skills for Agentic Tasks
- Agent Workflow Memory
- SkillSmith: Compiling Agent Skills into Boundary-Guided Runtime Interfaces
- ReAct: Synergizing Reasoning and Acting in Language Models
- UFO: A UI-Focused Agent for Windows OS Interaction
- Synapse: Trajectory-as-Exemplar Prompting with Memory for Computer Control
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
- Agents' Last Exam
- 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