WebChoreArena adds 532 human-curated, memory-intensive tasks to WebArena's reproducible environments, and current LLM agents score 2.6% to 44.9%, much lower than on WebArena.
Mind2web: Towards a generalist agent for the web
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
dataset 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1roles
dataset 1polarities
use dataset 1representative citing papers
citing papers explorer
-
WebChoreArena: Evaluating Web Browsing Agents on Realistic Tedious Web Tasks
WebChoreArena adds 532 human-curated, memory-intensive tasks to WebArena's reproducible environments, and current LLM agents score 2.6% to 44.9%, much lower than on WebArena.