% IMPORTANT: The following is UTF-8 encoded.  This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.

@INPROCEEDINGS{Saraiva:285736,
      author       = {Saraiva, Joao and Dyrba, Martin and Kirste, Thomas},
      title        = {{I}ntegrating {L}arge {L}anguage {M}odels with {F}ormal
                      {P}lanning to {A}utomate the {D}esign and {V}alidation of
                      {B}iosignal {P}rocessing {P}ipelines},
      publisher    = {IEEE},
      reportid     = {DZNE-2026-00293},
      pages        = {806 - 812},
      year         = {2025},
      comment      = {2025 IEEE 37th International Conference on Tools with
                      Artificial Intelligence (ICTAI) : [Proceedings] - IEEE,
                      2025. - ISBN 979-8-3315-4919-0 -
                      doi:10.1109/ICTAI66417.2025.00117},
      booktitle     = {2025 IEEE 37th International
                       Conference on Tools with Artificial
                       Intelligence (ICTAI) : [Proceedings] -
                       IEEE, 2025. - ISBN 979-8-3315-4919-0 -
                       doi:10.1109/ICTAI66417.2025.00117},
      abstract     = {Robust analysis of biosignals hinges on well-crafted
                      processing pipelines, yet assembling them is still a slow,
                      errorprone exercise, requiring both domain expertise and
                      programming skills. While Large Language Models (LLMs) offer
                      promising assistance, they fundamentally lack the
                      combinatorial reasoning capabilities needed for designing
                      reliable and reproducible processing pipelines. We present
                      an innovative hybrid system that harnesses LLMs' natural
                      language understanding while leveraging classical AI
                      planning for logical reasoning and validation. A
                      retrieval-augmented model parses natural language pipeline
                      descriptions into implementation-independent atomic
                      biosignal processing operations, which follow to a
                      Hierarchical Task Network (HTN) domain that can plan and
                      validate processing workflows, as well as flag violations of
                      biosignal processing best practices. Evaluation on a
                      preliminary corpus of scenarios demonstrates 0. 8 9 - 0. 9 8
                      precision in mapping natural language to processing blocks
                      and 0.97-0.98 F1-score in generating valid 2-15 step
                      pipelines using SHOP3 planner. A drag-and-drop pipeline
                      design interface allows users to build and formally validate
                      their pipeline ideas from scratch, showing potential to
                      democratize and expedite biosignal analysis for scientists
                      of different backgrounds.},
      month         = {Nov},
      date          = {2025-11-03},
      organization  = {2025 IEEE 37th International
                       Conference on Tools with Artificial
                       Intelligence, Athens (Greece), 3 Nov
                       2025 - 5 Nov 2025},
      cin          = {AG Teipel},
      cid          = {I:(DE-2719)1510100},
      pnm          = {353 - Clinical and Health Care Research (POF4-353)},
      pid          = {G:(DE-HGF)POF4-353},
      typ          = {PUB:(DE-HGF)8 / PUB:(DE-HGF)7},
      doi          = {10.1109/ICTAI66417.2025.00117},
      url          = {https://pub.dzne.de/record/285736},
}