Mint-Agent: Introducing Finance-Native Agentic Foundation Models
2026-08-17 • Computation and Language
Computation and LanguageMachine Learning
AI summaryⓘ
The authors created Mint-Agent, a set of AI models specialized for finance that focus on being both reliable and able to carry out long, complex research steps that can be checked later. They built the system with three key parts: clean financial data, a stable environment to test ideas, and a smart way to train the models by combining different learning methods. Their final models, Mint-Cu and Mint-Ag, scored higher than other top AI systems on professional finance tests, showing they can perform precise and trustworthy financial tasks. The work shows how to design AI that handles expert financial knowledge while keeping clear evidence of its reasoning.
Financial AI agentsLong-horizon executionAuditable evidenceSupervised fine-tuning (SFT)Reinforcement learning with value ranking (RLVR)Model mergingOn-policy distillationFinancial benchmarksDomain expertiseAgentic models
Authors
Mint-Agent Team, B. Zhang, Yaze Geng, Lei Tang, Yaoyang Yi, Zonghan Wu, Yifan Hu, Kun Wang, Qingsong Wen, Yilei Shao
Abstract
Financial agents must do more than recall domain knowledge: they must be both reliable, executing precise operations over grounded evidence, and executive, sustaining long-horizon research whose conclusions remain auditable. We present Mint-Agent, a family of finance-native agentic models designed around these two scales of financial intelligence. Mint-Agent is built upon three pillars: data, harness, and algorithm. Our data engine constructs clean, specialized tasks for atomic financial capabilities and long-horizon agentic execution from real-world financial sources. MintHarness enables stable interaction with open-ended environments and maintains auditable evidence trails across extended research trajectories. Our training recipe combines SFT, critical-step OPD, and RLVR to develop separate financial reasoning and agentic execution experts, which are then unified through model merging and multi-teacher on-policy distillation into compact, general-purpose financial agents. This pipeline yields two flagship models, Mint-Cu (9B) and Mint-Ag (27B). Across professional financial benchmarks, our models demonstrate two defining strengths: (1) Reliability: Mint-Ag achieves 98.33% on RFC-Bench, surpassing GPT-5.6-Sol and Claude-Opus-4.8 by 3.66 and 3.00 points; and (2) Executability: Mint-Cu reaches 69.86% on FinSearchComp T2, outperforming Agents-A1-35B and Nex-N2-mini by 22.83 and 12.78 points, while Mint-Ag achieves 76.00% and 60.49% on FinanceAgentBench v1.1 and v2, respectively. These results establish a path toward trustworthy financial intelligence in which domain expertise, long-horizon execution, and auditable evidence are jointly engineered as a unified foundation for frontier agentic models.