WebXSkill: Skill Learning for Autonomous Web Agents

arXiv:2604.13318 · cs.AI, cs.CL · Submitted 2026-04-14 · Read on arXiv

cs.AI, cs.CL

Submitted: 2026-04-14

Updated: 2026-08-31

Comments: Accepted to Findings of EMNLP2026

Code: https://github.com/aiming-lab/WebXSkill

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Grounding — 9× in this paper · explained in 3 episodes
• Abstraction — 6× in this paper · explained in 1 episode
• Adaptation — 6× in this paper · explained in 1 episode
• Accuracy — 5× in this paper · explained in 1 episode
• Benchmark — 5× in this paper · explained in 2 episodes
• AI Agents — 3× in this paper · explained in 2 episodes
• Ablation — 3× in this paper · explained in 1 episode
• Action Space — 3× in this paper · explained in 1 episode
• Adam — 3× in this paper · explained in 2 episodes
• Foundation Model — 3× in this paper · explained in 3 episodes
• Large Language Models (LLMs) — 3× in this paper · explained in 6 episodes
• Reinforcement Learning — 3× in this paper · explained in 4 episodes
• Ablation study — 2× in this paper · explained in 1 episode
• Adaptability — 2× in this paper · explained in 1 episode
• Invocation Rate — 2× in this paper
• Procedural Knowledge — 2× in this paper · explained in 2 episodes
• Robustness — 2× in this paper · explained in 5 episodes
• Transferability — 2× in this paper · explained in 4 episodes
• Agentic Task — 1× in this paper · explained in 1 episode
• Agentic Tasks — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Core — 1× in this paper · explained in 2 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Graceful Degradation — 1× in this paper · explained in 2 episodes
• Hallucination — 1× in this paper · explained in 4 episodes
• Multi-agent Collaborative Framework — 1× in this paper · explained in 2 episodes
• Usage Rate — 1× in this paper
• Vision-language models — 1× in this paper · explained in 2 episodes
• alpha — 1× in this paper · explained in 1 episode

Sources

• Agent S2: A Compositional Generalist-Specialist Framework for Computer Use Agents
• Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
• Mind2Web: Towards a Generalist Agent for the Web
• PAL: Program-aided Language Models
• OpenWebVoyager: Building Multimodal Web Agents via Iterative Real-World Exploration, Feedback and Optimization
• WebSailor: Navigating Super-human Reasoning for Web Agent
• ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform Data
• UI-R1: Enhancing Efficient Action Prediction of GUI Agents by Reinforcement Learning
• NNetNav: Unsupervised Learning of Browser Agents Through Environment Interaction in the Wild
• WebGPT: Browser-assisted question-answering with human feedback
• A Survey of WebAgents: Towards Next-Generation AI Agents for Web Automation with Large Foundation Models
• Explorer: Scaling Exploration-driven Web Trajectory Synthesis for Multimodal Web Agents
• OpenAI GPT-5 System Card
• SteP: Stacked LLM Policies for Web Actions
• CoAct-1: Computer-using Multi-Agent System with Coding Actions
• OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis
• Agent Workflow Memory
• WebAgent-R1: Training Web Agents via End-to-End Multi-Turn Reinforcement Learning
• PlugMem: A Task-Agnostic Plugin Memory Module for LLM Agents
• GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL

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
• 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
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection