Region4Web shows that shifting web agent observation to functional regions instead of element-level granularity produces shorter, more effective state representations and raises task success on WebArena across multiple LLMs and agent methods.
Mind2web: Towards a generalist agent for the web
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
dataset 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
dataset 1polarities
use dataset 1representative citing papers
Empirical study finds background semantics, random pruning, and recency-based allocation improve token efficiency for GUI visual agents.
citing papers explorer
-
Region4Web: Rethinking Observation Space Granularity for Web Agents
Region4Web shows that shifting web agent observation to functional regions instead of element-level granularity produces shorter, more effective state representations and raises task success on WebArena across multiple LLMs and agent methods.
-
Rethinking Token Pruning for Historical Screenshots in GUI Visual Agents: Semantic, Spatial, and Temporal Perspectives
Empirical study finds background semantics, random pruning, and recency-based allocation improve token efficiency for GUI visual agents.