Metraipolis › archive › dc_ad8d176fa232

Mint-Agent: Introducing Finance-Native Agentic Foundation Models — arXiv:2608.16386

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.16386
License (as archived): CC0-1.0
Archived: 2026-10-18T18:59:07.779Z
SHA-256 of the archived text: 19cc022a10c25c5355ed59bcaba67353bfb2f2eabace3a0e0001b419b1d2b767
Stable URL of this page: https://metraipolis.com/documento/dc_ad8d176fa232

How to cite

Mint-Agent: Introducing Finance-Native Agentic Foundation Models — arXiv:2608.16386 — arXiv (en), https://arxiv.org/abs/2608.16386 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ad8d176fa232 (Metraipolis archive dc_ad8d176fa232, sha256 19cc022a10c25c5355ed59bcaba67353bfb2f2eabace3a0e0001b419b1d2b767)

BibTeX

@misc{dcad8d176fa232,
  title = {Mint-Agent: Introducing Finance-Native Agentic Foundation Models — arXiv:2608.16386},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.16386},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ad8d176fa232; sha256 19cc022a10c25c5355ed59bcaba67353bfb2f2eabace3a0e0001b419b1d2b767},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.16386. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.16386 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-18T18:06:57.894Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).