InterAct: Exploring the Potentials of ChatGPT as a Cooperative Agent
This work addresses improving task planning in AI agents for real-world applications, but it is incremental as it focuses on prompt engineering with existing models.
The paper tackles the problem of integrating ChatGPT into embodied agent systems for interactive decision-making, achieving a 98% success rate on AlfWorld tasks in a simulated household environment.
This research paper delves into the integration of OpenAI's ChatGPT into embodied agent systems, evaluating its influence on interactive decision-making benchmark. Drawing a parallel to the concept of people assuming roles according to their unique strengths, we introduce InterAct. In this approach, we feed ChatGPT with varied prompts, assigning it a numerous roles like a checker and a sorter, then integrating them with the original language model. Our research shows a remarkable success rate of 98% in AlfWorld, which consists of 6 different tasks in a simulated household environment, emphasizing the significance of proficient prompt engineering. The results highlight ChatGPT's competence in comprehending and performing intricate tasks effectively in real-world settings, thus paving the way for further advancements in task planning.