# Fino1: On the Transferability of Reasoning-Enhanced LLMs and Reinforcement Learning to Finance

arXiv: https://arxiv.org/abs/2502.08127 · HTML: https://mlsanity.com/paper/2502.08127/

## Key facts

- Cited by 35 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 28 of its 48 references that are in the map.
- First posted on arXiv 12 Feb 2025.

## 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, 28 of 28)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [Solving Quantitative Reasoning Problems with Language Models](https://mlsanity.com/paper/2206.14858/) (2022)
- [s1: Simple test-time scaling](https://mlsanity.com/paper/2501.19393/) (2025)
- [OpenAI o1 System Card](https://mlsanity.com/paper/2412.16720/) (2024)
- [Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement](https://mlsanity.com/paper/2409.12122/) (2024)
- [BloombergGPT: A Large Language Model for Finance](https://mlsanity.com/paper/2303.17564/) (2023)
- [DeepSeek-V3 Technical Report](https://mlsanity.com/paper/2412.19437/) (2024)
- [FinQA: A Dataset of Numerical Reasoning over Financial Data](https://mlsanity.com/paper/2109.00122/) (2021)
- [LIMO: Less is More for Reasoning](https://mlsanity.com/paper/2502.03387/) (2025)
- [HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs](https://mlsanity.com/paper/2412.18925/) (2024)
- [FinGPT: Open-Source Financial Large Language Models](https://mlsanity.com/paper/2306.06031/) (2023)
- [ReFT: Reasoning with Reinforced Fine-Tuning](https://mlsanity.com/paper/2401.08967/) (2024)
- [ConvFinQA: Exploring the Chain of Numerical Reasoning in Conversational Finance Question Answering](https://mlsanity.com/paper/2210.03849/) (2022)
- [TheoremQA: A Theorem-driven Question Answering dataset](https://mlsanity.com/paper/2305.12524/) (2023)
- [Generalized Preference Optimization: A Unified Approach to Offline Alignment](https://mlsanity.com/paper/2402.05749/) (2024)
- [FinBen: A Holistic Financial Benchmark for Large Language Models](https://mlsanity.com/paper/2402.12659/) (2024)
- [Evaluation of OpenAI o1: Opportunities and Challenges of AGI](https://mlsanity.com/paper/2409.18486/) (2024)
- [Automatic Prompt Augmentation and Selection with Chain-of-Thought from Labeled Data](https://mlsanity.com/paper/2302.12822/) (2023)
- [DocFinQA: A Long-Context Financial Reasoning Dataset](https://mlsanity.com/paper/2401.06915/) (2024)
- [Open-FinLLMs: Open Multimodal Large Language Models for Financial Applications](https://mlsanity.com/paper/2408.11878/) (2024)
- [What do neural networks learn in image classification? A frequency shortcut perspective](https://mlsanity.com/paper/2307.09829/) (2023)
- [Automate Strategy Finding with LLM in Quant Investment](https://mlsanity.com/paper/2409.06289/) (2024)
- [EconLogicQA: A Question-Answering Benchmark for Evaluating Large Language Models in Economic Sequential Reasoning](https://mlsanity.com/paper/2405.07938/) (2024)

## Built on by (most cited first, 30 of 35)

- [Fin-R1: A Large Language Model for Financial Reasoning through Reinforcement Learning](https://mlsanity.com/paper/2503.16252/) (2025)
- [DianJin-R1: Evaluating and Enhancing Financial Reasoning in Large Language Models](https://mlsanity.com/paper/2504.15716/) (2025)
- [FinChain: A Symbolic Benchmark for Verifiable Chain-of-Thought Financial Reasoning](https://mlsanity.com/paper/2506.02515/) (2025)
- [Trading-R1: Financial Trading with LLM Reasoning via Reinforcement Learning](https://mlsanity.com/paper/2509.11420/) (2025)
- [AceSearcher: Bootstrapping Reasoning and Search for LLMs via Reinforced Self-Play](https://mlsanity.com/paper/2509.24193/) (2025)
- [Fin-RATE: A Real-world Financial Analytics and Tracking Evaluation Benchmark for LLMs on SEC Filings](https://mlsanity.com/paper/2602.07294/) (2026)
- [Alpha-R1: Alpha Screening with LLM Reasoning via Reinforcement Learning](https://mlsanity.com/paper/2512.23515/) (2025)
- [QuantEval: A Benchmark for Financial Quantitative Tasks in Large Language Models](https://mlsanity.com/paper/2601.08689/) (2026)
- [Reward Modeling for Reinforcement Learning-Based LLM Reasoning: Design, Challenges, and Evaluation](https://mlsanity.com/paper/2602.09305/) (2026)
- [Agentar-Fin-R1: Enhancing Financial Intelligence through Domain Expertise, Training Efficiency, and Advanced Reasoning](https://mlsanity.com/paper/2507.16802/) (2025)
- [The Illusion of Specialization: Unveiling the Domain-Invariant "Standing Committee" in Mixture-of-Experts Models](https://mlsanity.com/paper/2601.03425/) (2026)
- [FinCoT: Grounding Chain-of-Thought in Expert Financial Reasoning](https://mlsanity.com/paper/2506.16123/) (2025)
- [Reasoning on Time-Series for Financial Technical Analysis](https://mlsanity.com/paper/2511.08616/) (2025)
- [FinReporting: An Agentic Workflow for Localized Reporting of Cross-Jurisdiction Financial Disclosures](https://mlsanity.com/paper/2604.05966/) (2026)
- [FinWorld: An All-in-One Open-Source Platform for End-to-End Financial AI Research and Deployment](https://mlsanity.com/paper/2508.02292/) (2025)
- [Data Science and Technology Towards AGI Part I: Tiered Data Management](https://mlsanity.com/paper/2602.09003/) (2026)
- [Conv-FinRe: A Conversational and Longitudinal Benchmark for Utility-Grounded Financial Recommendation](https://mlsanity.com/paper/2602.16990/) (2026)
- [QuantCode-Bench: A Benchmark for Evaluating the Ability of Large Language Models to Generate Executable Algorithmic Trading Strategies](https://mlsanity.com/paper/2604.15151/) (2026)
- [Through the Judge's Eyes: Inferred Thinking Traces Improve Reliability of LLM Raters](https://mlsanity.com/paper/2510.25860/) (2025)
- [FinGuard: Detecting Financial Regulatory Non-Compliance in LLM Interactions](https://mlsanity.com/paper/2605.29427/) (2026)
- [FEVO: Financial Knowledge Expansion and Reasoning Evolution for Large Language Models](https://mlsanity.com/paper/2507.06057/) (2025)
- [ReasonAny: Incorporating Reasoning Capability to Any Model via Simple and Effective Model Merging](https://mlsanity.com/paper/2601.05560/) (2026)
- [BankMathBench: A Benchmark for Numerical Reasoning in Banking Scenarios](https://mlsanity.com/paper/2602.17072/) (2026)
- [Document-Level Numerical Reasoning across Single and Multiple Tables in Financial Reports](https://mlsanity.com/paper/2604.03664/) (2026)
- [Reasoning through Verifiable Forecast Actions: Consistency-Grounded RL for Financial LLMs](https://mlsanity.com/paper/2605.21975/) (2026)
- [DataPrep-Bench: Benchmarking LLMs as Training Data Preparators](https://mlsanity.com/paper/2607.20465/) (2026)
- [BizFinBench.v2: Towards Reliable LLMs in Finance via Real-User Data and Offline/Online Bilingual Evaluation](https://mlsanity.com/paper/2601.06401/) (2026)
- [Structure First, Reason Next: Enhancing a Large Language Model using Knowledge Graph for Numerical Reasoning in Financial Documents](https://mlsanity.com/paper/2601.07754/) (2026)
- [StakeBench: Evaluating Language Understanding Grounded in Market Commitment](https://mlsanity.com/paper/2605.26074/) (2026)
- [MoCA-Agent: A Market-of-Claims Code Agent for Financial and Numerical Reasoning](https://mlsanity.com/paper/2606.11537/) (2026)

## Abstract (arXiv)

As the fundamental capability behind decision-making in finance, financial reasoning poses distinct challenges for LLMs. Although reinforcement learning (RL) have boosted generic reasoning, the progress in finance is hindered by the absence of empirical study of building effective financial chain-of-thought (CoT) corpus, a systematic comparison of different RL methods, and comprehensive benchmarks. To address these gaps, we introduce FinCoT, the first open high-fidelity CoT corpus for finance, distilled from seven QA datasets by a novel three-stage pipeline that incorporates domain supervision, iterative LLM refinement, and difficulty-aware filtering. Based on FinCoT, we develop Fin-o1, the first open financial reasoning models trained via supervised fine-tuning and GRPO-based RL. Our models outperform existing financial reasoning models and SOTA general models such as GPT-o1, DeepSeek-R1, and GPT-4.5. We also investigate the effectiveness of three different RL methods in improving domain-specific reasoning, offering the first such empirical study. We finally propose FinReason, the first financial reasoning benchmark covering multi-table analysis, long-context reasoning, and equation-based tasks, and evaluate 29 LLMs. Our extensive experiments reveal general reasoning models excel on standard benchmarks yet exhibit obvious performance degradation in financial contexts; even finance-tuned models like Dianjin-R1 and FinR1 degrade on lengthy documents. In contrast, our Fin-o1 models consistently outperform their backbones and larger GPT-o1 and DeepSeek-R1, confirming the effectiveness of our data building and model training strategy. Our study further shows that GRPO yields reliable gains whereas PPO and DPO do not, highlighting the need for targeted data and optimisation rather than scale alone.