Work2Skill: Capturing Human GUI Experience for Reusable Agent Skill Induction
cs.AI, cs.HC
Submitted: 2026-10-09
Updated: 2026-10-09
Code: https://github.com/china-qijizhifeng/Work2Skill
Sources
- Agent S2: A Compositional Generalist-Specialist Framework for Computer Use Agents
- MyPCBench: A Benchmark for Personally Intelligent Computer-Use Agents
- LensWalk: Agentic Video Understanding by Planning How You See in Videos
- Instruction Agent: Enhancing Agent with Expert Demonstration
- Skill-Pro: Learning Reusable Skills from Experience via Non-Parametric PPO for LLM Agents
- Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills
- EvoClawBench: Can Agents Learn Reusable Skills from Their Own Runs?
- UI-TARS: Pioneering Automated GUI Interaction with Native Agents
- A Survey on (M)LLM-Based GUI Agents
- Inducing Programmatic Skills for Agentic Tasks
- SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning
- OmegaUse-SOP: SOP Engineering for Professional Computer Use from Human Demonstrations
- How Should Agents Read Demonstrations? Hierarchical Structure Beats Flat Action Logs
- Scalable Behaviour Cloning on Browser Using via Skill Distillation
- SkillForge: Evolving Verifiable Skills for Reinforcement Learning Agents
- AutoSkill: Experience-Driven Lifelong Learning via Skill Self-Evolution
- VideoExplorer: Think With Videos For Agentic Long-Video Understanding
- MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents
- MMSkills: Towards Multimodal Skills for General Visual Agents
- CUADebug: Diagnosing and Repairing Computer-Use Agent Failures
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