WebArena-Lite

WebArena-Lite is a dataset/benchmark used to evaluate the performance of large language model-based agents in web navigation tasks, particularly focusing on their ability to handle dynamic content and long sequences of actions.

Papers using WebArena-Lite (4)

WebAgent-R1: Training Web Agents via End-to-End Multi-Turn Reinforcement Learning2025 · 1 citesPlan-and-Act: Improving Planning of Agents for Long-Horizon Tasks2025 · 1 citesA Subgoal-driven Framework for Improving Long-Horizon LLM Agents2026Web-Shepherd: Advancing PRMs for Reinforcing Web Agents2025