EUVIMEDEUVIMED entdecken
Crossref

A-X-MAS: An Auditable, Explainable Multi-Agent System Design and Implementation

Yutong Yang, Yuping Wang

Academic Conferences Series · 2026-01 · 17 (1)

DOI: 10.62381/acs.emis2026.26 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Academic Conferences Series, 2026-01. Verfasst von Yutong Yang und 1 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recent advancements in artificial intelligence have promoted the application of multi-agent systems in complex decision-making scenarios. However, the adoption of such systems in high-stakes domains including cross-organizational process management is limited by insufficient transparency and auditability. This paper presents the design, implementation, and evaluation of A-X-MAS, an Auditable and Explainable Multi-Agent System. The framework adopts a five-agent architecture consisting of the Coordination Agent, Data Gathering Agent, Analysis Agents, Explainability Agent, and Audit Agent. The interaction protocols and workflows are formally defined using sequence diagrams and structured pseudocode. A large language model serves as the reasoning backbone for agent inference and natural language understanding, and human-readable explanation generation—enabling flexible parsing of unstructured financial data, semantic alignment of cross-organizational task requirements, and interpretable decision rationales. A self-optimization mechanism is constructed to adjust system parameters based on real-time performance feedback. Comparative experiments are conducted on a cross-border supply chain finance risk assessment dataset. Results indicate that the proposed system outperforms conventional methods in processing efficiency, decision accuracy, auditability, and explainability.

Zitieren

APA

Yang, Y., & Wang, Y. (2026). A-X-MAS: An Auditable, Explainable Multi-Agent System Design and Implementation. Academic Conferences Series, 17(1). https://doi.org/10.62381/acs.emis2026.26

Vancouver

Yang Y, Wang Y. A-X-MAS: An Auditable, Explainable Multi-Agent System Design and Implementation. Academic Conferences Series. 2026;17(1). doi:10.62381/acs.emis2026.26

BibTeX
@article{Yang2026,
  author = {Yang, Yutong and Wang, Yuping},
  title = {A-X-MAS: An Auditable, Explainable Multi-Agent System Design and Implementation},
  journal = {Academic Conferences Series},
  year = {2026},
  volume = {17},
  number = {1},
  doi = {10.62381/acs.emis2026.26}
}
Kostenlos starten →