Neuro-Symbolic Computer Use: Learning Reusable Policies for Reliable and Efficient Execution
cs.AI
Submitted: 2026-09-29
Updated: 2026-09-29
Code: https://github.com/microsoft/playwright
Sources
- Agent S2: A Compositional Generalist-Specialist Framework for Computer Use Agents
- On the Reliability of Computer Use Agents
- Scaling Agents for Computer Use
- Robotic Ultra-Long-Horizon Manipulation Skills via Human-guided Lifelong Code Generation
- Code as Agent Harness
- UI-TARS: Pioneering Automated GUI Interaction with Native Agents
- ALRM: Agentic LLM for Robotic Manipulation
- ScienceBoard: Evaluating Multimodal Autonomous Agents in Realistic Scientific Workflows
- UI-Venus-1.5 Technical Report
- Voyager: An Open-Ended Embodied Agent with Large Language Models
- OpenCUA: Open Foundations for Computer-Use Agents
- $\tau$-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains
- OSWorld 2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks
- SkillWeaver: Web Agents can Self-Improve by Discovering and Honing Skills
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