WorkArena L-1

Emerging

1papers using it

2026first seen

The 'WorkArena L-1' dataset/benchmark contains a set of tasks designed to evaluate the performance of web agents, specifically focusing on the impact of HTML observation reduction methods on agent latency and success rates.

🔎 Find this dataset

Papers using WorkArena L-1 (1)

Revisiting Observation Reduction for Web Agents: Comprehensive Evaluation with a Lightweight Framework2026