Ego2web Egocentric Web Agent Benchmark

Evaluate web agents on tasks grounded in first-person video perception with Ego2Web benchmark. Bridges egocentric video understanding and web agent execution across e-commerce and knowledge lookup domains. Includes Ego2WebJudge LLM-based evaluator achieving 84% human agreement, replacing unreliable domain-specific metrics. Reveals weak agent performance on physically-grounded tasks, highlighting the necessity of accurate multimodal visual understanding.

adu2021 Updated 7 repo stars

File contents

adu2021/skillxiv commit d3774771c6

Frequently asked questions

npx get-skill add adu2021/ego2web-egocentric-web-agent-benchmark