# FinSTaR: Towards Financial Reasoning with Time Series Reasoning Models

arXiv: https://arxiv.org/abs/2605.03460 · HTML: https://mlsanity.com/paper/2605.03460/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 15 of its 35 references that are in the map.
- First posted on arXiv 5 May 2026.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)

## Builds on (most cited first, 15 of 15)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024)
- [Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone](https://mlsanity.com/paper/2404.14219/) (2024)
- [Fin-R1: A Large Language Model for Financial Reasoning through Reinforcement Learning](https://mlsanity.com/paper/2503.16252/) (2025)
- [MTBench: A Multimodal Time Series Benchmark for Temporal Reasoning and Question Answering](https://mlsanity.com/paper/2503.16858/) (2025)
- [Towards Time Series Reasoning with LLMs](https://mlsanity.com/paper/2409.11376/) (2024)
- [TimeART: Towards Agentic Time Series Reasoning via Tool-Augmentation](https://mlsanity.com/paper/2601.13653/) (2026)
- [Time-R1: Towards Comprehensive Temporal Reasoning in LLMs](https://mlsanity.com/paper/2505.13508/) (2025)
- [FinTSB: A Comprehensive and Practical Benchmark for Financial Time Series Forecasting](https://mlsanity.com/paper/2502.18834/) (2025)
- [Thoth: Mid-Training Bridges LLMs to Time Series Understanding](https://mlsanity.com/paper/2603.01042/) (2026)
- [FinZero: Launching Multi-modal Financial Time Series Forecast with Large Reasoning Model](https://mlsanity.com/paper/2509.08742/) (2025)

## Built on by (most cited first, 4 of 4)

- [EXAONE Finance 1.0: An Attention-free Time Series Foundation Model for Financial Time Series](https://mlsanity.com/paper/2609.04239/) (2026)
- [ReasonCast: Towards Explainable Time Series Forecasting with Reasoning](https://mlsanity.com/paper/2608.01875/) (2026)
- [Explaining Time Series Forecasting with Horizon-Resolved Attribution](https://mlsanity.com/paper/2609.12639/) (2026)
- [PALM: Point-in-Time Adaptation for Financial Language Models](https://mlsanity.com/paper/2609.30316/) (2026)

## Abstract (arXiv)

Time series (TS) reasoning models (TSRMs) have shown promising capabilities in general domains, yet they consistently fail on financial domain, which exhibit unique characteristics. We propose a general 2 x 2 capability taxonomy for TSRMs by crossing 1) single-entity vs. multi-entity analysis with 2) assessment of the current state vs. prediction of future behavior. We instantiate this taxonomy in the financial domain---where the distinction between deterministic assessment and stochastic prediction is particularly critical---as ten financial reasoning tasks, forming the FinTSRBench benchmark based on S&P stocks. To this end, we propose FinSTaR (Financial Time Series Thinking and Reasoning), trained on FinTSR-Bench with distinct chain-of-thought (CoT) strategies tailored to each category. For assessment, which is deterministic, we employ Compute-in-CoT, a programmatic CoT that enables models to derive answers directly from raw prices. For prediction, which is inherently stochastic, we adopt Scenario-Aware CoT, which generates diverse scenarios before making a judgment, mirroring how financial analysts reason under uncertainty. FinSTaR achieves 78.9% average accuracy on FinTSRBench, substantially outperforming LLM and TSRM baselines. Furthermore, we show that the four capability categories are complementary and mutually reinforcing through joint training. Code is publicly available at: https://github.com/seunghan96/FinSTaR.