AutoPlan: Automatic Planning of Interactive Decision-Making Tasks With Large Language Models
–arXiv.org Artificial Intelligence
Recent large language models (LLMs) are promising for making decisions in grounded environments. However, LLMs frequently fail in complex decision-making tasks due to the misalignment between the pre-trained knowledge in LLMs and the actual rules in the environment. Existing methods require either costly gradient computation or lengthy in-context demonstrations. In this paper, we propose AutoPlan, an approach to guide LLM-based agents to accomplish interactive decision-making tasks. AutoPlan augments the LLM prompt with a task-solving plan and optimizes it through iterative experience collection and reflection. Our experiments show that AutoPlan, though using no in-context demonstrations, achieves success rates on par with the baselines using human-written demonstrations on ALFWorld and even outperforms them by 8% on HotpotQA. The code is available at https://github.com/owaski/AutoPlan.
arXiv.org Artificial Intelligence
Oct-26-2023
- Country:
- Europe
- Belgium > Brussels-Capital Region
- Brussels (0.04)
- Ireland > Leinster
- County Dublin > Dublin (0.04)
- Belgium > Brussels-Capital Region
- North America > United States
- California > Santa Barbara County
- Santa Barbara (0.04)
- District of Columbia > Washington (0.04)
- Pennsylvania > Allegheny County
- Pittsburgh (0.04)
- California > Santa Barbara County
- Europe
- Genre:
- Research Report (0.82)
- Industry:
- Leisure & Entertainment > Games (0.46)
- Technology: