Enregistré dans:
Détails bibliographiques
Auteurs principaux: Pehlke, Marcel, Jansen, Marc
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2511.07086
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866918193818238976
author Pehlke, Marcel
Jansen, Marc
author_facet Pehlke, Marcel
Jansen, Marc
contents We present a modular, explainable LLM-agent pipeline for decision support that externalizes reasoning into auditable artifacts. The system instantiates three frameworks: Vester's Sensitivity Model (factor set, signed impact matrix, systemic roles, feedback loops); normal-form games (strategies, payoff matrix, equilibria); and sequential games (role-conditioned agents, tree construction, backward induction), with swappable modules at every step. LLM components (default: GPT-5) are paired with deterministic analyzers for equilibria and matrix-based role classification, yielding traceable intermediates rather than opaque outputs. In a real-world logistics case (100 runs), mean factor alignment with a human baseline was 55.5\% over 26 factors and 62.9\% on the transport-core subset; role agreement over matches was 57\%. An LLM judge using an eight-criterion rubric (max 100) scored runs on par with a reconstructed human baseline. Configurable LLM pipelines can thus mimic expert workflows with transparent, inspectable steps.
format Preprint
id arxiv_https___arxiv_org_abs_2511_07086
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LLM Driven Processes to Foster Explainable AI
Pehlke, Marcel
Jansen, Marc
Artificial Intelligence
We present a modular, explainable LLM-agent pipeline for decision support that externalizes reasoning into auditable artifacts. The system instantiates three frameworks: Vester's Sensitivity Model (factor set, signed impact matrix, systemic roles, feedback loops); normal-form games (strategies, payoff matrix, equilibria); and sequential games (role-conditioned agents, tree construction, backward induction), with swappable modules at every step. LLM components (default: GPT-5) are paired with deterministic analyzers for equilibria and matrix-based role classification, yielding traceable intermediates rather than opaque outputs. In a real-world logistics case (100 runs), mean factor alignment with a human baseline was 55.5\% over 26 factors and 62.9\% on the transport-core subset; role agreement over matches was 57\%. An LLM judge using an eight-criterion rubric (max 100) scored runs on par with a reconstructed human baseline. Configurable LLM pipelines can thus mimic expert workflows with transparent, inspectable steps.
title LLM Driven Processes to Foster Explainable AI
topic Artificial Intelligence
url https://arxiv.org/abs/2511.07086