Preprint

Mint-Agent: Introducing Finance-Native Agentic Foundation Models

Mint-Agent Team Kun Wang Gavin Zhang Yaze Geng Lei Tang Yaoyang Yi Zonghan Wu Yifan Hu Qingsong Wen Yi Shao

Aug 2026 · 0 citations · 93 references

Computer Science

TL;DR

Mint-Agent, a family of finance-native agentic models designed around these two scales of financial intelligence, is presented, establishing 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.

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.

arXiv Semantic Scholar

View source

Similar papers

Jul 2026

FORCE-Bench: A Benchmark, Dataset, and Evaluation Harness for Agentic AI in Enterprise Finance

This work introduces FORCE-Bench, which contains 251 expert-annotated queries and evaluates responses using a rubric-based framework calibrated to the requirements of the operational finance domain, across eight dimensions: accuracy, citations, clarity, depth, groundedness, recency, relevance, and structure.

Wolfgang M. Pauli, Sarah Panda, Kidus Admassu et al. · arXiv.org · 2 citations

Preprint Aug 2026

Prime Agent: A Self-Improving RLM Harness

Low-friction, expressive membrane prevents harness failures from becoming model failures and pushes measurement toward the model's true maximal underlying capability, on Factorio, where refinement allows for continuous technology progression and dedicated subagents enable parallelized work.

Seth Karten, Alex L. Zhang, Kevin Thomas et al. · 2 citations · ⚡1

#artificial intelligence Preprint Sep 2026

Agentic Empirical Asset Pricing: Methodological Foundations

Recent advances in LLM agents enable a new paradigm for asset pricing, which we call Agentic Empirical Asset Pricing (AEAP): systems that autonomously conduct the scientific discovery process itself. We define AEAP and identify its core building blocks. Existing evaluation practices backtest only the outputs (factors or trades), not the autonomous discovery system that produced them. We focus on factor discovery, contributing a reference architecture, a rigorous evaluation standard for discovered factors, and a method for out-of-sample backtesting the discovery system. As a concrete instance of that architecture, we evaluate SEADS against five re-implemented baselines on two US equity panels using this standard: no single metric ranks the systems consistently, motivating evaluation on multiple axes at once. A separate rolling re-execution then asks the complementary question of whether the discovery process itself, not one static output, is reliable. We also report negative findings and limitations that surface further evaluation pitfalls for future AEAP systems.

Ying-Jian Pan, Xiao-Wei Ding, Kay Giesecke · 0 citations

#artificial intelligence Preprint Sep 2026

MASkills: Continual Skills Optimization for Multi-Agent LLM Systems

LLM-based multi-agent systems have shown strong performance on complex tasks, yet continual improvement from interaction experience remains challenging. Existing self-reflection methods build experience memories, but memories are mostly hard to invoke, refine, or scale, while agent skills offer a more actionable unit: structured procedural knowledge that specifies when to act, how to act, and which resources or tools to use. We introduce MASkills, a continual learning framework that optimizes multi-agent LLM systems through agent skills. MASkills presents a new agent-optimization pipeline that integrates skill-conditioned credit assignment, hierarchical credit aggregation, and momentum-smoothed optimization, enabling agent skill libraries to evolve through refinement, induction, consolidation, and pruning. Experiments on HotpotQA, LoCoMo, and GAIA demonstrate the effectiveness of MASkills across multiple agentic tasks. Our code is available at https://github.com/DaRL-GenAI/MASkills

Huaiyuan Yao, Xiaoou Liu, Charles Fleming et al. · 0 citations

Jul 2026

From Memory to Skills: Evidence-Grounded Co-Evolution Governance for Long-Horizon LLM Agents

This paper proposes MSCE, a training-free Memory--Skill Co-Evolution framework that organizes agent experience into grounded step traces, reusable procedural policies, and declarative environmental cognition, and introduces reflection-weighted value backfilling.

Bo Tang, Yang Zhang, Guomian Zhuang et al. · arXiv.org · 1 citation

Jul 2026

NextFund: A Unified Performance Tracking Platform for Agentic Portfolio Management

This work introduces NextFund, an evaluation platform that makes financial-agent behavior observable under live market conditions, and presents NextFund on Hong Kong, U.S., and China A-share equities, illustrating how inspectable decision histories enable fairer benchmarking and more actionable diagnosis.

Changlun Li, Peixian Ma, Qiqi Duan et al. · arXiv.org · 1 citation