@inproceedings{qu-etal-2025-category,
    title = "A Category-Theoretic Approach to Neural-Symbolic Task Planning with Bidirectional Search",
    author = "Qu, Shuhui  and
      Wang, Jie  and
      Law, Kincho",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.1157/",
    doi = "10.18653/v1/2025.findings-emnlp.1157",
    pages = "21201--21225",
    ISBN = "979-8-89176-335-7",
    abstract = "We introduce a \textit{Neural-Symbolic Task Planning} framework integrating Large Language Model (LLM) decomposition with category-theoretic verification for resource-aware, temporally consistent planning. Our approach represents states as objects and valid operations as morphisms in a categorical framework, ensuring constraint satisfaction through mathematical pullbacks. We employ bidirectional search that simultaneously expands from initial and goal states, guided by a learned planning distance function that efficiently prunes infeasible paths. Empirical evaluations across three planning domains demonstrate that our method improves completion rates by up to 6.6{\%} and action accuracy by 9.1{\%}, while eliminating resource violations compared to the existing baselines. These results highlight the synergy between LLM-based operator generation and category-theoretic verification for reliable planning in domains requiring both resource-awareness and temporal consistency."
}