Agentar-Fin-R1: Enhancing Financial Intelligence through Domain Expertise, Training Efficiency, and Advanced Reasoning

TL;DR

Agentar-Fin-R1 models significantly improve financial reasoning, trustworthiness, and training efficiency through specialized optimization, comprehensive validation, and new evaluation benchmarks, demonstrating state-of-the-art performance in financial AI applications.

Contribution

Introducing the Agentar-Fin-R1 series, which enhances reasoning, reliability, and domain adaptation of LLMs for finance using innovative training and validation frameworks.

Findings

Achieved state-of-the-art results on financial benchmarks.

Demonstrated superior reasoning capabilities on general datasets.

Validated high trustworthiness and efficiency in training processes.

Abstract

Large Language Models (LLMs) exhibit considerable promise in financial applications; however, prevailing models frequently demonstrate limitations when confronted with scenarios that necessitate sophisticated reasoning capabilities, stringent trustworthiness criteria, and efficient adaptation to domain-specific requirements. We introduce the Agentar-Fin-R1 series of financial large language models (8B and 32B parameters), specifically engineered based on the Qwen3 foundation model to enhance reasoning capabilities, reliability, and domain specialization for financial applications. Our optimization approach integrates a high-quality, systematic financial task label system with a comprehensive multi-layered trustworthiness assurance framework. This framework encompasses high-quality trustworthy knowledge engineering, multi-agent trustworthy data synthesis, and rigorous data validation governance. Through label-guided automated difficulty-aware optimization, tow-stage training pipeline, and dynamic attribution systems, we achieve substantial improvements in training efficiency. Our models undergo comprehensive evaluation on mainstream financial benchmarks including Fineva, FinEval, and FinanceIQ, as well as general reasoning datasets such as MATH-500 and GPQA-diamond. To thoroughly assess real-world deployment capabilities, we innovatively propose the Finova evaluation benchmark, which focuses on agent-level financial reasoning and compliance verification. Experimental results demonstrate that Agentar-Fin-R1 not only achieves state-of-the-art performance on financial tasks but also exhibits exceptional general reasoning capabilities, validating its effectiveness as a trustworthy solution for high-stakes financial applications. The Finova bench is available at https://github.com/antgroup/Finova.