EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Just-in-Time Historical State Reconstruction for Low-Latency Financial Trading with Large Language Models

Dong Hoang Van, Md Monjurul Karim, Qiang Qu

AI · 27.03.2026 · 7 (4) · 117

DOI: 10.3390/ai7040117 ↗

Kurz gefasst

Fachartikel in der Zeitschrift AI, online erschienen am 27.03.2026. Verfasst von Dong Hoang Van und 2 weiteren Autor:innen. Die Arbeit nennt 16 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key Research and Development Program of China, Basic and Applied Basic Research Foundation of Guangdong Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper introduces Historical State Reconstruction, a novel framework for low-latency financial decision-making using Large Language Models. While agentic systems have demonstrated potential in synthesizing complex financial narratives, they typically rely on Retrieval-Augmented Generation or memory-based architectures. These paradigms introduce significant latency and risk look-ahead bias during real-time inference, rendering them unsuitable for high-frequency trading environments where milliseconds determine profitability. This proposed framework resolves this bottleneck by decoupling the heavy computational cost of context acquisition from the latency-sensitive critical path of decision-making. We propose a system that proactively compiles unstructured regulatory filings (10-K, 10-Q, 8-K) into a structured, bitemporal database. By pre-computing complex state facets, such as financial health ratios, governance structures, and insider trading signals offline, the system allows trading agents to “time travel” to a reconstructed state at any historical moment t with O(1) snapshot retrieval plus O(k) delta application complexity. We implement this approach on the top 50 companies in the S&P 500 ranked by market capitalization, processing over 12,000 filings to demonstrate a pipeline that transforms high-dimensional financial narratives into compact, prompt-ready context. Our evaluation shows that the system reduces context retrieval latency by over 97% compared to traditional baselines while achieving a 300:1 compression ratio for financial health data. Furthermore, the bitemporal architecture guarantees strict temporal integrity, eliminating the risk of data leakage in backtesting and satisfying the reproducibility requirements of regulatory frameworks like SR 11-7.

Förderung

  • National Key Research and Development Program of China
  • Basic and Applied Basic Research Foundation of Guangdong Province

Zitieren

APA

Van, D. H., Karim, M. M., & Qu, Q. (2026). Just-in-Time Historical State Reconstruction for Low-Latency Financial Trading with Large Language Models. AI, 7(4), 117. https://doi.org/10.3390/ai7040117

Vancouver

Van DH, Karim MM, Qu Q. Just-in-Time Historical State Reconstruction for Low-Latency Financial Trading with Large Language Models. AI. 2026;7(4):117. doi:10.3390/ai7040117

BibTeX
@article{Van2026,
  author = {Van, Dong Hoang and Karim, Md Monjurul and Qu, Qiang},
  title = {Just-in-Time Historical State Reconstruction for Low-Latency Financial Trading with Large Language Models},
  journal = {AI},
  year = {2026},
  volume = {7},
  number = {4},
  pages = {117},
  doi = {10.3390/ai7040117}
}
Kostenlos starten →