WebArena

WebArena is a benchmark dataset used to evaluate the performance of large language models in long-horizon tasks by assessing their ability to manage context and reduce information entropy during multi-turn interactions.

Papers using WebArena (9)

Escaping the Context Bottleneck: Active Context Curation for LLM Agents via Reinforcement Learning2026OpAgent: Operator Agent for Web Navigation2026Just-In-Time Reinforcement Learning: Continual Learning in LLM Agents Without Gradient Updates2026DynaWeb: Model-Based Reinforcement Learning of Web Agents2026Scaling Agent Learning via Experience Synthesis2025SkyRL-Agent: Efficient RL Training for Multi-turn LLM Agent2025WEBSERV: A Full-Stack and RL-Ready Web Environment for Training Web Agents at Scale2025Thinking vs. Doing: Agents that Reason by Scaling Test-Time Interaction2025WebPilot: A Versatile and Autonomous Multi-Agent System for Web Task Execution with Strategic Exploration2024 · 4 cites