Structured Agentic Workflows for Financial Time-Series Modeling with LLMs and Reflective Feedback

TL;DR

This paper presents TS-Agent, a modular agentic framework that automates and improves financial time-series modeling by combining structured decision processes, reasoning, and feedback, leading to better accuracy, interpretability, and robustness.

Contribution

The paper introduces TS-Agent, a novel structured agentic system that enhances financial time-series modeling workflows with iterative decision-making, knowledge-guided exploration, and adaptive learning capabilities.

Findings

Outperforms state-of-the-art AutoML in accuracy and robustness.

Supports adaptive learning and transparent auditing in financial modeling.

Demonstrates effectiveness on diverse forecasting and synthetic data tasks.

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.