Structured Agentic Workflows for Financial Time-Series Modeling with LLMs and Reflective Feedback
Year: 2025
Type: preprint
Abstract: Time-series data is central to decision-making in financial markets, yet building high-performing, interpretable, and auditable models remains a major challenge. While Automated Machine Learning (AutoML) frameworks streamline model development, they often lack adaptability and responsiveness to domain-specific needs and evolving objectives. Concurrently, Large Language Models (LLMs) have enabled agentic systems capable of reasoning, memory management, and dynamic code generation, offering a path toward more flexible workflow automation. In this paper, we introduce \textsf{TS-Agent}, a modular agentic framework designed to automate and enhance time-series modeling workflows for financial applications. The agent formalizes the pipeline as a structured, iterative decision process across three stages: model selection, code refinement, and fine-tuning, guided by contextual reasoning and experimental feedback. Central to our architecture is a planner agent equipped with structured knowledge banks, curated libraries of models and refinement strategies, which guide exploration, while improving interpretability and reducing error propagation. \textsf{TS-Agent} supports adaptive learning, robust debugging, and transparent auditing, key requirements for high-stakes environments such as financial services. Empirical evaluations on diverse financial forecasting and synthetic data generation tasks demonstrate that \textsf{TS-Agent} consistently outperforms state-of-the-art AutoML and agentic baselines, achieving superior accuracy, robustness, and decision traceability.
Source: arXiv (Cornell University)
Authors: Ang, Yihao, Bao, Yifan, Jiang, Lei, Tao, Jiajie, Tung, Anthony K. H., Szpruch, Lukasz, Ni, Hao
Language: English
Field: Decision Sciences
Domain: Social Sciences
Open Access status: green
Awards: FAIR: Framework for responsible adoption of Artificial Intelligence in the financial seRvices industry, G1309768829, G1633672591, G2677699893, G3481878861, G3855435662, G444630160, The Alan Turing Institute, G8581904048, Unparameterised multi-modal data, high order signatures, and the mathematics of data science
OpenAlex ID: W4415014129
Cites:
Cited by:
Related to: