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

Time-series data drives financial decision-making, yet building models that are simultaneously high-performing, interpretable, and auditable remains challenging. Automated Machine Learning (AutoML) streamlines development but often lacks domain adaptivity, while recent LLM-based agents enable end-to-end workflow automation. 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. Across financial forecasting and synthetic generation tasks, it consistently outperforms state-of-the-art AutoML and agentic baselines in accuracy, robustness, and decision traceability.