McGill NLP releases WebArena-Pro browser agent benchmark
McGill NLP and Mila researchers released WebArena-Pro, a self-hostable and reproducible multimodal benchmark with 300-400 tasks across 20 popular websites, addressing the limited site coverage of earlier benchmarks and accepted to NeurIPS 2026.
2026-11-16 ~ 2026-11-17 · 4 related posts
- WebArena-Pro: a 300-task multimodal benchmark across 20 self-hosted apps for web agents — McGill-NLP · 2026-11-16
- WebArena-Pro launches: 300-task multimodal web-agent benchmark across 20 apps — xhluca · 2026-11-16
- WebArena-Pro launches: 400 tasks across 20 real websites for browser agents — xhluca · 2026-11-17
1 near-duplicate retellings: xhluca