@inproceedings{banerjee-gupta-2025-personalized,
    title = "Personalized open world plan generation for safety-critical human centered autonomous systems: A case study on Artificial Pancreas",
    author = "Banerjee, Ayan  and
      Gupta, Sandeep",
    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.1219/",
    doi = "10.18653/v1/2025.findings-emnlp.1219",
    pages = "22409--22422",
    ISBN = "979-8-89176-335-7",
    abstract = "Design-time safety guarantees for human-centered autonomous systems (HCAS) often break down in open-world deployment due to uncertain human interaction. In practice, HCAS must follow a user-personalized safety plan, with the human providing external inputs to handle out-of-distribution events. Open-world safety planning for HCAS demands modeling dynamical systems, exploring novel actions, and rapid replanning when plans are invalidated or dynamics shift. No single state-of-the-art planner meets all these needs. We introduce an LLM-based architecture that automatically generates personalized safety plans. By itself, the LLM fares poorly at producing safe usage plans, but coupling it with a safety verifier{---}which evaluates plan safety over the planning horizon and feeds back quality scores{---}enables the discovery of safe plans. Moreover, fine-tuning the LLM on personalized models inferred from open-world data further enhances plan quality. We validate our approach by generating safe usage plans for artificial pancreas systems in automated insulin delivery for Type 1 Diabetes patients. Code: https://github.com/ImpactLabASU/LLMOpen"
}