arXiv AI
WebXSkill: Skill Learning for Autonomous Web Agents
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Jun 17
Beyond Domains: Reusing Web Skills via Transferable Interaction Patterns
arXiv:2606. 17645v1 Announce Type: new Abstract: Large language model (LLM) web agents are usually deployed as tool callers: each turn, the model reads a fresh page observation and emits one structured tool action.
arXiv Computer Vision
Oct 27
Back to Basics: A Skill-Centric Approach to Generalist Web Agents
arXiv:2610.35823v1 Announce Type: new Abstract: Browser agents do not just need more practice. They need to practice the right things. We introduce MiniWeb, a realistic miniature of the web comprisin...
arXiv AI
Jun 4
Online Skill Learning for Web Agents via State-Grounded Dynamic Retrieval
arXiv:2606. 04391v1 Announce Type: new Abstract: Language agents increasingly rely on reusable skills to improve multi-step web automation across related tasks.
arXiv AI
Sep 10
SCAFFOLD: Self-Improving Web Agents via Recursive Parametric Skill Abstraction
SCAFFOLD is a self‑improving framework for visual web agents that automatically induces parametric, executable skills from successful trajectories and organizes them into a recursively composed hierarchy. It compresses the skill library using a minimum‑description‑length criterion and behavioral equivalence checks, and periodically distills these skills back into model weights to internalize the abstractions. Experiments on WebArena, VisualWebArena, and Online‑Mind2Web show that SCAFFOLD raises success rates by 11.1–17.2 absolute points over the best skill‑augmented baseline and continues to improve across five self‑improvement iterations without collapsing the library.
arXiv AI
Oct 27
SkillShift-Bench: Benchmarking Skill Learning under Environment Evolution for Web Agents
SkillShift-Bench is a new benchmark that evaluates web agents’ skill learning under controlled open-environment shifts, including Contextual, Perceptual, and Execution shifts across three self-hosted web systems. It measures task success, interaction cost, skill use, and skill failure, revealing that skill robustness degrades systematically—especially under Execution Shift. The benchmark also frames shifted skill execution as a nonstationary local executability problem, offering a dynamic-regret analysis and a test-time adaptation method to improve skill execution without relearning.
arXiv AI
Aug 10
WebGrader: Training LLMs for Web Development with Self-Evolving Programmatic Grader
arXiv:2608. 06474v1 Announce Type: new Abstract: Large language models increasingly generate complete websites from natural-language descriptions, and reinforcement learning has become a central approach to closing their remaining functional gap.