With advances in generative AI, there is now potential for autonomous agents to manage daily tasks via natural language commands. However, current agents are primarily created and tested in simplified synthetic environments, leading to a disconnect with real-world scenarios. In this paper, we build an environment for language-guided agents that is highly realistic and reproducible. Specifically, we focus on agents that perform tasks on the web, and create an environment with fully functional websites from four common domains: e-commerce, social forum discussions, collaborative software development, and content management. Our environment is enriched with tools (e.g., a map) and external knowledge bases (e.g., user manuals) to encourage human-like task-solving. Building upon our environment, we release a set of benchmark tasks focusing on evaluating the functional correctness of task completions. The tasks in our benchmark are diverse, long-horizon, and designed to emulate tasks that humans routinely perform on the internet. We experiment with several baseline agents, integrating recent techniques such as reasoning before acting. The results demonstrate that solving complex tasks is challenging: our best GPT-4-based agent only achieves an end-to-end task success rate of 14.41%, significantly lower than the human performance of 78.24%. These results highlight the need for further development of robust agents, that current state-of-the-art large language models are far from perfect performance in these real-life tasks, and that WebArena can be used to measure such progress.

Boids Building autonomous agents to simulate group motion and obstacle avoidance such as activities of bird flocks and schools of fish. Excalibur This project develops a generic architecture for a group of agents to pursue their given goals, adapt their behavior to new environments, and communicate and perform coordinated group actions. Artificial Life Interactive Video Environment (MIT) The Artificial Life Interactive Video Environment (ALIVE) is virtual reality system where people can interact with virtual creatures without being constrained by headsets, goggles, or special sensing equipment. The system is based on a magic mirror metaphore: a person in the ALIVE space sees their own image in a large-screen TV as if in a mirror. Autonomous, animated characters join the user's own image in the reflected world.