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

arXiv: https://arxiv.org/abs/2508.13915 · HTML: https://mlsanity.com/paper/2508.13915/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Placed in Financial trading and forecasting agents, one of 16 directions in LLM agents and tool use.
- Builds on 14 of its 33 references that are in the map.
- First posted on arXiv 19 Aug 2025.

## Placed in

- LLM agents and tool use / [Financial trading and forecasting agents](https://mlsanity.com/agents/financial-trading-and-forecasting-agents/)

## Builds on (most cited first, 14 of 14)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Optuna: A Next-generation Hyperparameter Optimization Framework](https://mlsanity.com/paper/1907.10902/) (2019)
- [A Time Series is Worth 64 Words: Long-term Forecasting with Transformers](https://mlsanity.com/paper/2211.14730/) (2022)
- [Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting](https://mlsanity.com/paper/2106.13008/) (2021)
- [Are Transformers Effective for Time Series Forecasting?](https://mlsanity.com/paper/2205.13504/) (2022)
- [Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networks](https://mlsanity.com/paper/1703.07015/) (2017)
- [Real-valued (Medical) Time Series Generation with Recurrent Conditional GANs](https://mlsanity.com/paper/1706.02633/) (2017)
- [ResearchAgent: Iterative Research Idea Generation over Scientific Literature with Large Language Models](https://mlsanity.com/paper/2404.07738/) (2024)
- [TimeVAE: A Variational Auto-Encoder for Multivariate Time Series Generation](https://mlsanity.com/paper/2111.08095/) (2021)
- [Sig-Wasserstein GANs for Time Series Generation](https://mlsanity.com/paper/2111.01207/) (2021)
- [TSGBench: Time Series Generation Benchmark](https://mlsanity.com/paper/2309.03755/) (2023)
- [PCF-GAN: generating sequential data via the characteristic function of measures on the path space](https://mlsanity.com/paper/2305.12511/) (2023)
- [CTBench: Cryptocurrency Time Series Generation Benchmark](https://mlsanity.com/paper/2508.02758/) (2025)

## Built on by (most cited first, 9 of 9)

- [MOSAIC: Modular Orchestration for Structured Agentic Intelligence and Composition](https://mlsanity.com/paper/2606.00708/) (2026)
- [OpenFinGym: A Verifiable Multi-Task Gym Environment for Evaluating Quant Agents](https://mlsanity.com/paper/2606.26350/) (2026)
- [GenAutoML: An Agentic Framework for Dynamic Architecture Generation and Optimization in Time-Series Analysis](https://mlsanity.com/paper/2606.05860/) (2026)
- [A Framework for Assessing AI Agent Decisions and Outcomes in AutoML Pipelines](https://mlsanity.com/paper/2602.22442/) (2026)
- [Empowering VLMs for Few-Shot Multimodal Time Series Classification via Tailored Agentic Reasoning](https://mlsanity.com/paper/2605.09395/) (2026)
- [Neuro-Agentic Control: A Deep Learning-based LLM-Powered Agentic AI Framework for Controlling Security Controls](https://mlsanity.com/paper/2607.09076/) (2026)
- [EvoTS-Agent: A Self-Evolving LLM Agent for Financial Time Series Change Point Detection](https://mlsanity.com/paper/2608.17933/) (2026)
- [Self-Evolving Time-Series Forecasting Agents with Episodic Memory and Online Policy Learning](https://mlsanity.com/paper/2609.32689/) (2026)
- [Agent Policy-Value Audit: Separating Transition Composition from Event Selection in Financial LLM Agents](https://mlsanity.com/paper/2610.04040/) (2026)

## Abstract (arXiv)

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 textsfTS-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. textsfTS-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 textsfTS-Agent consistently outperforms state-of-the-art AutoML and agentic baselines, achieving superior accuracy, robustness, and decision traceability.