Contribution to a conference proceedings/Contribution to a book

DZNE-2026-00293

http://join2-wiki.gsi.de/foswiki/pub/Main/Artwork/join2_logo100x88.png Integrating Large Language Models with Formal Planning to Automate the Design and Validation of Biosignal Processing Pipelines

Saraiva, J.Extern* ; Dyrba, M.DZNE* ; Kirste, T.

2025
IEEE

This record in other databases:  

Please use a persistent id in citations: 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.

---

Contributing Institute(s):

1. Clinical Dementia Research (Rostock /Greifswald) (AG Teipel)

Research Program(s):

1. 353 - Clinical and Health Care Research (POF4-353) (POF4-353)

---