Metraipolis › archive › dc_89a8892ffb76

iCoder-27B: Recursive AI-Led Development of Frontier Industrial Coding Model — arXiv:2609.29626

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.29626
License (as archived)
CC0-1.0
Archived
2026-10-08T04:26:17.569Z
SHA-256 of the archived text
2f4358340d7f2671c608ad0d552e46205b89c1ec5de3fa9faf871003f152aa68
Stable URL of this page
https://metraipolis.com/documento/dc_89a8892ffb76

How to cite

iCoder-27B: Recursive AI-Led Development of Frontier Industrial Coding Model — arXiv:2609.29626 — arXiv (en), https://arxiv.org/abs/2609.29626 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_89a8892ffb76 (Metraipolis archive dc_89a8892ffb76, sha256 2f4358340d7f2671c608ad0d552e46205b89c1ec5de3fa9faf871003f152aa68)
BibTeX
@misc{dc89a8892ffb76,
  title = {iCoder-27B: Recursive AI-Led Development of Frontier Industrial Coding Model — arXiv:2609.29626},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.29626},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_89a8892ffb76; sha256 2f4358340d7f2671c608ad0d552e46205b89c1ec5de3fa9faf871003f152aa68},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.29626. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Recursive AI, the prospect of AI taking an increasingly complete role in building and improving AI, is a crown jewel of AI for AI. Although recursive self-development has become practical for small models, bounded tasks, and fixed time budgets, a more consequential realization of this ambition, i.e., developing a release-ready, frontier-competitive model, remains far more challenging. In this work, we ask how little human involvement is sufficient for an agent to develop a frontier model. We concentrate human input into a high-density, low-frequency interface: experts encode objectives, stage scaffolds, permission boundaries, and operating procedures as reusable research skills, while the agent instantiates these priors, selects experiments, diagnoses outcomes, and revises the training strategy. In the challenging domain of industrial coding, the agent evolves data and coordinates SFT, on-policy self-distillation, and reinforcement learning with verifiable rewards, ultimately producing iCoder, a 27B model for RTL design and GPU kernel optimization. Across seven benchmarks, iCoder leads RTLLM, outperforming GPT-5.5 and Claude-Opus-4.8; ranks second on CVDP and KernelBench L2, exceeding GPT-5.5 by 16 points; and ties Claude-Opus-4.8 for the best TritonBench result. Exploratory case studies further show iCoder's competitive iterative RTL and GPU-kernel optimization with substantially fewer tokens. These results chart an engineering path toward recursive self-improvement, in which humans distill the principles of model building, agents operationalize them through evidence-driven experimentation, and each generation of AI becomes a more capable architect of the next.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-25 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL); Software Engineering (cs.SE).
Pagina del lavoro: https://arxiv.org/abs/2609.29626 — 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 2026-10-08T03:50:57.809Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).