Make Planning Research Rigorous Again!

TL;DR

This paper advocates for applying rigorous design and evaluation practices from traditional planning research to the development of large language model-based planners, emphasizing the importance of community insights and avoiding past pitfalls.

Contribution

It highlights the need to incorporate established planning community insights into LLM-based planner development to ensure rigor and avoid common pitfalls.

Findings

Traditional planning practices can improve LLM-based planner development.

Community insights are crucial for avoiding known pitfalls.

Rigorous evaluation methods are essential for progress.

Abstract

In over sixty years since its inception, the field of planning has made significant contributions to both the theory and practice of building planning software that can solve a never-before-seen planning problem. This was done through established practices of rigorous design and evaluation of planning systems. It is our position that this rigor should be applied to the current trend of work on planning with large language models. One way to do so is by correctly incorporating the insights, tools, and data from the automated planning community into the design and evaluation of LLM-based planners. The experience and expertise of the planning community are not just important from a historical perspective; the lessons learned could play a crucial role in accelerating the development of LLM-based planners. This position is particularly important in light of the abundance of recent works that replicate and propagate the same pitfalls that the planning community has encountered and learned from. We believe that avoiding such known pitfalls will contribute greatly to the progress in building LLM-based planners and to planning in general.