SkillMigrator learns reusable web skills by matching layout structures instead of specific element references. It stores each skill as a transferable interaction pattern (TIP) with a structural sketch, enabling efficient skill reuse across sites. Compared to state-of-the-art methods, it reduces average LLM-action counts by 8-10% on WebArena and Mind2Web at matched success rates.
arxiv
arXiv cs.CL
·
8d ago
·
research
SkillMigrator Enables Cross-Site Web Skill Transfer via Layout Matching
from English
Importance 3/3
Beats a top-lab benchmark
New feature vs. leaders
New harness with differentiators
arXiv cs.CL
OpenAI
Google DeepMind
Mistral AI
AI agents
Evaluation & benchmarks
Reasoning models
Benchmarks
| Benchmark | Model | Score |
|---|---|---|
| WebArena | SkillMigrator | 8% |