EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Governed Hierarchical Memory and Uncertainty-Triggered Routing for Cost-Efficient Financial Sentiment Decision Support

Jianxing Zhang, Bin Ma, Lei Ai, Xinyi Song, Jiayu Cheng, Jianan Li, Zhuting Yu

Systems · 01.11.2026 · 14 (11) · 1377

DOI: 10.3390/systems14111377 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Systems, online erschienen am 01.11.2026. Verfasst von Jianxing Zhang und 6 weiteren Autor:innen. Die Arbeit nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key Research Program of China, Shanghai Municipal Commission of Science and Technology Research Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Financial decision-support systems must balance quality, cost, traceability, and controlled state reuse. Existing single-agent, retrieval-augmented, and always-on multi-agent pipelines leave the joint control of collaboration and shared-memory activation under-specified. The purpose of this study is to determine whether governed hierarchical memory with uncertainty-triggered routing can preserve financial sentiment quality while reducing coordination cost. We operationalize uncertainty with an input-derived ambiguity score: after a low-cost probe, below-threshold inputs short circuit, whereas flagged inputs escalate to governed collaboration. On the disjoint 2064-record remainder of Financial PhraseBank sentences_allagree, the proposed configuration achieves 0.9453 accuracy and 0.9364 macro-F1—within 0.0005 and 0.0006, respectively, of the direct baseline—while using 63.57% fewer tokens than always-on collaboration but 31.05% more than direct inference. Earlier 200-record development and agreement-shifted analyses are highly label-skewed and are treated as sensitivity evidence only. Ablations and trace audits identify routing as the measured source of efficiency; no isolated benchmark gain is attributable to the governance rule. Theoretically, the study separates computational activation from governed state reuse as control-plane mechanisms. Practically, managers can reserve collaboration for flagged inputs while retaining traceability, although the ambiguity proxy and governed-memory benefits require harder workflow validation.

Förderung

  • National Key Research Program of China
  • Shanghai Municipal Commission of Science and Technology Research Project

Zitieren

APA

Zhang, J., Ma, B., Ai, L., Song, X., Cheng, J., Li, J., & Yu, Z. (2026). Governed Hierarchical Memory and Uncertainty-Triggered Routing for Cost-Efficient Financial Sentiment Decision Support. Systems, 14(11), 1377. https://doi.org/10.3390/systems14111377

Vancouver

Zhang J, Ma B, Ai L, Song X, Cheng J, Li J, et al. Governed Hierarchical Memory and Uncertainty-Triggered Routing for Cost-Efficient Financial Sentiment Decision Support. Systems. 2026;14(11):1377. doi:10.3390/systems14111377

BibTeX
@article{Zhang2026,
  author = {Zhang, Jianxing and Ma, Bin and Ai, Lei and Song, Xinyi and Cheng, Jiayu and Li, Jianan and Yu, Zhuting},
  title = {Governed Hierarchical Memory and Uncertainty-Triggered Routing for Cost-Efficient Financial Sentiment Decision Support},
  journal = {Systems},
  year = {2026},
  volume = {14},
  number = {11},
  pages = {1377},
  doi = {10.3390/systems14111377}
}
Kostenlos starten →