Model Space Reasoning as Search in Feedback Space for Planning Domain Generation
For AI planning researchers, this work provides a method to generate usable planning domains from natural language, though the gains are incremental over existing LLM-based approaches.
The paper tackles the problem of generating planning domains from natural language descriptions. By using an agentic language model feedback framework with symbolic feedback (landmarks, VAL plan validator) and heuristic search over model space, they improve domain quality, achieving higher validity and plan quality compared to baselines.
The generation of planning domains from natural language descriptions remains an open problem even with the advent of large language models and reasoning models. Recent work suggests that while LLMs have the ability to assist with domain generation, they are still far from producing high quality domains that can be deployed in practice. To this end, we investigate the ability of an agentic language model feedback framework to generate planning domains from natural language descriptions that have been augmented with a minimal amount of symbolic information. In particular, we evaluate the quality of the generated domains under various forms of symbolic feedback, including landmarks, and output from the VAL plan validator. Using these feedback mechanisms, we experiment using heuristic search over model space to optimize domain quality.