{"ID":2843955,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.07086","arxiv_id":"2511.07086","title":"LLM Driven Processes to Foster Explainable AI","abstract":"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.","short_abstract":"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, equilibri...","url_abs":"https://arxiv.org/abs/2511.07086","url_pdf":"https://arxiv.org/pdf/2511.07086v1","authors":"[\"Marcel Pehlke\",\"Marc Jansen\"]","published":"2025-11-10T13:20:00Z","proceeding":"cs.AI","tasks":"[\"cs.AI\"]","methods":"[\"Large Language Model\"]","has_code":false}