Skip to main content Skip to main navigation

Publikation

EXAR: A Unified Experience-Grounded Agentic Reasoning Architecture

Ralph Bergmann; Florian Brand; Mirko Lenz; Lukas Malburg
In: Isabelle Bichindaritz; Beatriz Lopez (Hrsg.). Case-Based Reasoning Research and Development. International Conference on Case-Based Reasoning (ICCBR-2025), Cham, France, Lecture Notes in Computer Science (LNCS), Springer Nature Switzerland, 2025.

Zusammenfassung

Current AI reasoning often relies on static pipelines (like the 4R cycle from Case-Based Reasoning (CBR) or standard RetrievalAugmented Generation (RAG)) that limit adaptability. We argue it is time for a shift towards dynamic, experience-grounded agentic reasoning. This paper proposes EXAR, a new unified, experience-grounded architecture, conceptualizing reasoning not as a fixed sequence, but as a collaborative process orchestrated among specialized agents. EXAR integrates data and knowledge sources into a persistent Long-Term Memory utilized by diverse reasoning agents, which coordinate themselves via a Short-Term Memory. Governed by an Orchestrator and Meta Learner, EXAR enables flexible, context-aware reasoning strategies that adapt and improve over time, offering a blueprint for next-generation AI.