Inducing Programmatic Skills for Agentic Tasks

This paper proposes Agent Skill Induction (ASI), which learns executable program-based skills online from web interaction experience and reuses them as tasks evolve. The use of programs makes skill induction verifiable, improving both WebArena success rate and step efficiency over static agents and text-skill baselines while also supporting cross-website transfer.

• Why Generate a Click? Plug-in Decision Heads for Web Agents
  October 14, 2026 · arXiv
• Teaching Agents in their Own Style: Blackbox Teacher Distillation for Web Agents
  October 14, 2026 · arXiv
• AutoTailor: Automatic, User-Aligned Capability Selection and Adaptation for Web Agents
  September 11, 2026 · arXiv
• ColorBrowserAgent: Complex Long-Horizon Browser Agent with Adaptive Knowledge Evolution
  January 12, 2026 · arXiv
• Towards Enterprise-Ready Computer Using Generalist Agent
  February 24, 2025 · arXiv
• SteP: Stacked LLM Policies for Web Actions
  October 5, 2023 · COLM 2024
• Back to Basics: A Skill-Centric Approach to Generalist Web Agents
  October 26, 2026 · arXiv
• Step-Aligned Script Generation with Verification and Recovery for Web Automation Testing
  October 19, 2026 · arXiv
• What It Is, Not What It Says: Securing Agentic Browsing Interactions with Web Semantics
  October 15, 2026 · arXiv
• STP-GUI: Spatially-Aware Token Pruning for Efficient Web-GUI Agents
  October 14, 2026 · arXiv
• Work2Skill: Capturing Human GUI Experience for Reusable Agent Skill Induction
  October 9, 2026 · arXiv
• Right Screen, Wrong Transition: World Models as Verifiers for GUI Agents
  October 8, 2026 · arXiv
• CLIFT: Conformal Self-Verification for Web Agent Training and Test-Time Scaling
  October 5, 2026 · arXiv
• AMBER: Training Long-Horizon Web Agents through Append-Only Memory
  October 5, 2026 · arXiv
• TeleTune: Evolving Agent Skills From Offline Telemetry
  October 4, 2026 · arXiv
• One Rollout Is All You Get: Fully Test-Time Adaptation for GUI Agents
  September 28, 2026 · arXiv
• Guides That Cause Actions: An Offline Study of Guide-Action Mutual Reinforcement in Multimodal Web Agents
  September 23, 2026 · arXiv
• Routing Is Least Learnable Where It Is Most Valuable: Bounds on Representation Routing for Web Agents
  August 6, 2026 · arXiv
• Online Skill Learning for Web Agents via State-Grounded Dynamic Retrieval
  June 3, 2026 · arXiv
• The Tool Illusion: Rethinking Tool Use in Web Agents
  April 3, 2026 · arXiv
• When Users Change Their Mind: Evaluating Interruptible Agents in Long-Horizon Web Navigation
  April 1, 2026 · arXiv
• WebArena-Infinity: Generating Browser Environments with Verifiable Tasks at Scale
  March 2026 · Blog Post
• AI Planning Framework for LLM-Based Web Agents
  March 13, 2026 · arXiv
• HATS: Hardness-Aware Trajectory Synthesis for GUI Agents
  March 12, 2026 · CVPR 2026