The Future of Planning: How AI Can Help Us Find the Best Solution
Imagine a coffee company trying to optimize its supply chain. The company sources beans from three suppliers, roasts them at two facilities into either dark or light coffee, and then ships the roasted coffee to three retail locations. The suppliers have different fixed capacity, and roasting costs and shipping costs vary from place to place. The company seeks to minimize costs while meeting a 23 percent increase in demand. Wouldn’t it be easier for the company to just ask ChatGPT to come up with an optimal plan?
The Challenge of Planning
For all their incredible capabilities, large language models (LLMs) often perform poorly when tasked with directly solving complex planning problems on their own. This is because planning problems involve many interrelated decision variables, each with multiple options that rapidly add up to billions of potential choices.
A New Approach to Planning
MIT researchers took a different approach. They introduced a framework that guides an LLM to break down the problem like a human would, and then automatically solve it using a powerful software tool. The framework, called LLM-Based Formalized Programming (LLMFP), uses a natural language description of the problem, background information on the task, and a query that describes the user’s goal.
How LLMFP Works
Using LLMFP, a person provides a natural language description of the problem, background information on the task, and a query that describes their goal. Then, LLMFP prompts an LLM to reason about the problem and determine the decision variables and key constraints that will shape the optimal solution. LLMFP asks the LLM to detail the requirements of each variable before encoding the information into a mathematical formulation of an optimization problem.
The Power of LLMFP
During the formulation process, the LLM checks its work at multiple intermediate steps to make sure the plan is described correctly to the solver. If it spots an error, rather than giving up, the LLM tries to fix the broken part of the formulation. When the researchers tested their framework on nine complex challenges, it achieved an 85 percent success rate, whereas the best baseline only achieved a 39 percent success rate.
The Future of Planning
The versatile framework could be applied to a range of multistep planning tasks, such as scheduling airline crews or managing machine time in a factory. "Our research introduces a framework that essentially acts as a smart assistant for planning problems," says Yilun Hao, a graduate student in the MIT Laboratory for Information and Decision Systems (LIDS). "It can figure out the best plan that meets all the needs you have, even if the rules are complicated or unusual."
Conclusion
LLMFP has the potential to revolutionize the field of planning by making it easier for people to use powerful software tools to find the best solution to complex problems. With its ability to reason about problems and automatically solve them, LLMFP is an exciting development in the field of AI and planning. As the researchers continue to improve and refine their framework, we can expect to see even more impressive results in the future.
