Guardado en:
Detalles Bibliográficos
Autores principales: Oswald, James, Obolensky, Daniel, Varha, Volodymyr, Dragovic, Vasilije, Srinivas, Kavitha, Kokel, Harsha, Katz, Michael, Sohrabi, Shirin
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2604.08712
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915948251840512
author Oswald, James
Obolensky, Daniel
Varha, Volodymyr
Dragovic, Vasilije
Srinivas, Kavitha
Kokel, Harsha
Katz, Michael
Sohrabi, Shirin
author_facet Oswald, James
Obolensky, Daniel
Varha, Volodymyr
Dragovic, Vasilije
Srinivas, Kavitha
Kokel, Harsha
Katz, Michael
Sohrabi, Shirin
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2604_08712
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Model Space Reasoning as Search in Feedback Space for Planning Domain Generation
Oswald, James
Obolensky, Daniel
Varha, Volodymyr
Dragovic, Vasilije
Srinivas, Kavitha
Kokel, Harsha
Katz, Michael
Sohrabi, Shirin
Artificial Intelligence
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.
title Model Space Reasoning as Search in Feedback Space for Planning Domain Generation
topic Artificial Intelligence
url https://arxiv.org/abs/2604.08712