Mind2Web

The 'Mind-2Web' dataset/benchmark contains real-world web environments used to evaluate the performance of large language model (LLM) agents in decision-making tasks without relying on external demonstrations or fine-tuning.

Papers using Mind2Web (3)

Reflecting with Two Voices: A Co-Adaptive Dual-Strategy Framework for LLM-Based Agent Decision Making2025Auto-Intent: Automated Intent Discovery and Self-Exploration for Large Language Model Web Agents2024WEPO: Web Element Preference Optimization for LLM-based Web Navigation2024