// Skill Learning for Autonomous Web Agents // Web agents can navigate a page, but ask them to repeat a checkout flow they already completed…

// Skill Learning for Autonomous Web Agents // Web agents can navigate a page, but ask them to repeat a checkout flow they already completed, and they start from scratch every time. This work introduces WebXSkill, a skill learning framework where web agents extract reusable skills from synthetic trajectories. Each skill pairs a parameterized action program with step-level natural language guidance, making it both executable by the runtime and interpretable by the agent. Two deployment modes let the agent either auto-execute skills as atomic tool calls (grounded mode) or follow them as step-by-step instructions while retaining autonomy to adapt (guided mode). Results: - On WebArena, WebXSkill improves task success rate by up to 9.8 points over baselines (69.5% vs 59.7%). - On WebVoyager, grounded mode reaches 86.1%, a 14.2-point gain over vanilla agents. Skills even transfer across environments: guided mode using only WebArena-extracted skills scores 85.1% on WebVoyager. Stronger models benefit more from grounded execution, while weaker models gain more from guided mode, suggesting the deployment strategy should match model capability. Paper: https://arxiv.org/abs/2604.13318 Learn to build effective AI agents in our academy: https://academy.dair.ai/

Related

• WebXSkill: Skill Learning for Autonomous Web Agents
• // Scaling Coding Agents via Atomic Skills // Most coding agents train end-to-end on full tasks like resolving GitHub issues. But complex so…
• UI-AGILE: Advancing GUI Agents with Effective Reinforcement Learning and Precise Inference-Time Grounding
• MolmoWeb: Open Visual Web Agent and Open Data for the Open Web

Source: DAIR.AI (X) | 2026-04-17