Mint-Agent: Introducing Finance-Native Agentic Foundation Models

arXiv 2608.16386 ↗First posted 17 Aug 2026cs.CL cs.LGcited by 0

On the map: LLM agents and tool use → Financial trading and forecasting agents

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Financial trading and forecasting agents, one of 16 directions in LLM agents and tool use. Builds on 81 of its 93 references that are in the map. First posted on arXiv 17 Aug 2026.

Builds on

81 of 93 references.

Closest ancestors · 9

Same direction, newest first

Other references · 72

2026DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligencecited by 1,040
2023BloombergGPT: A Large Language Model for Financecited by 939
2025Group Sequence Policy Optimizationcited by 835
2023TIES-Merging: Resolving Interference When Merging Modelscited by 818
2021FinQA: A Dataset of Numerical Reasoning over Financial Datacited by 562
2021TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Financecited by 408
2023FinanceBench: A New Benchmark for Financial Question Answeringcited by 270
2023FinGPT: Open-Source Financial Large Language Modelscited by 253
2025Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learningcited by 237
2023PIXIU: A Large Language Model, Instruction Data and Evaluation Benchmark for Financecited by 222
2022ConvFinQA: Exploring the Chain of Numerical Reasoning in Conversational Finance Question Answeringcited by 196
2025Beyond Ten Turns: Unlocking Long-Horizon Agentic Search with Large-Scale Asynchronous RLcited by 150

38 more

2025ReSum: Unlocking Long-Horizon Search Intelligence via Context Summarizationcited by 141
2025Agent Lightning: Train ANY AI Agents with Reinforcement Learningcited by 109
2025AgentFold: Long-Horizon Web Agents with Proactive Context Managementcited by 103
2025Fin-R1: A Large Language Model for Financial Reasoning through Reinforcement Learningcited by 83
2026Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model Agentscited by 78
2026MOPD: Multi-Teacher On-Policy Distillation for Capability Integration in LLM Post-Trainingcited by 72
2025DeepAgent: A General Reasoning Agent with Scalable Toolsetscited by 71
2025Tongyi DeepResearch Technical Reportcited by 66
2025Finance Agent Benchmark: Benchmarking LLMs on Real-world Financial Research Taskscited by 65
2025Mem-α: Learning Memory Construction via Reinforcement Learningcited by 55
2025Scaling LLM Multi-turn RL with End-to-end Summarization-based Context Managementcited by 51
2025WebWeaver: Structuring Web-Scale Evidence with Dynamic Outlines for Open-Ended Deep Researchcited by 46
2026OpenSeeker: Democratizing Frontier Search Agents by Fully Open-Sourcing Training Datacited by 39
2025Look Back to Reason Forward: Revisitable Memory for Long-Context LLM Agentscited by 38
2026OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesiscited by 37
2025MUA-RL: Multi-turn User-interacting Agent Reinforcement Learning for agentic tool usecited by 32
2025Agent-R1: A Unified and Modular Framework for Agentic Reinforcement Learningcited by 29
2025MemSearcher: Training LLMs to Reason, Search and Manage Memory via End-to-End Reinforcement Learningcited by 27
2025QwenLong-L1.5: Post-Training Recipe for Long-Context Reasoning and Memory Managementcited by 27
2025BizFinBench: A Business-Driven Real-World Financial Benchmark for Evaluating LLMscited by 22
2026Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agentcited by 22
2025Learning When to Plan: Efficiently Allocating Test-Time Compute for LLM Agentscited by 20
2025RLFactory: A Plug-and-Play Reinforcement Learning Post-Training Framework for LLM Multi-Turn Tool-Usecited by 20
2025AWorld: Orchestrating the Training Recipe for Agentic AIcited by 17
2026CM2: Reinforcement Learning with Checklist Rewards for Multi-Turn and Multi-Step Agentic Tool Usecited by 14
2026Self-Evolving World Models for LLM Agent Planningcited by 13
2025Failure Makes the Agent Stronger: Enhancing Accuracy through Structured Reflection for Reliable Tool Interactionscited by 12
2025Step-DeepResearch Technical Reportcited by 12
2026Cited but Not Verified: Parsing and Evaluating Source Attribution in LLM Deep Research Agentscited by 12
2026QUEST: Training Frontier Deep Research Agents with Fully Synthetic Taskscited by 11
2026OpenThoughts-Agent: Data Recipes for Agentic Modelscited by 11
2025DeepTRACE: Auditing Deep Research AI Systems for Tracking Reliability Across Citations and Evidencecited by 10
2025Beyond the Strongest LLM: Multi-Turn Multi-Agent Orchestration vs. Single LLMs on Benchmarkscited by 9
2026Breaking the Tokenizer Barrier: On-Policy Distillation across Model Familiescited by 9
2026How to Train Your Deep Research Agent? Prompt, Reward, and Policy Optimization in Search-R1cited by 8
2026From Fluent to Verifiable: Claim-Level Auditability for Deep Research Agentscited by 7
2026Uno-Orchestra: Parsimonious Agent Routing via Selective Delegationcited by 6
2026Argus: Evidence Assembly for Scalable Deep Research Agentscited by 6

50 most cited of 72 All 72 (JSON)

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way