Pinned
Thanks for sharing our work.
We aim to enhance Web Agents by driving their reasoning and thinking through Web-CogKnowledge.
Welcome to follow our updates, we will open-source all model weights, datasets, and benchmarks eventually.
Most web agents still click around blindly because they never store real knowledge about page parts or user goals.
This work builds Web‑CogReasoner, an agent that learns in 3 clear rounds, memorize facts, grasp concepts, then practice procedures, and thinks through that stack
