Metraipolis › archive › dc_293e8788a883

Axion 1.0: Open Agent Foundation Models, Simplified — arXiv:2611.03233

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.03233
License (as archived)
CC0-1.0
Archived
2026-11-03T10:33:43.707Z
SHA-256 of the archived text
8dd0c807e44d55e14d59a3d0a7074c03bb2290e56d77e7a4de2865169b1d2057
Stable URL of this page
https://metraipolis.com/documento/dc_293e8788a883

How to cite

Axion 1.0: Open Agent Foundation Models, Simplified — arXiv:2611.03233 — arXiv (en), https://arxiv.org/abs/2611.03233 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_293e8788a883 (Metraipolis archive dc_293e8788a883, sha256 8dd0c807e44d55e14d59a3d0a7074c03bb2290e56d77e7a4de2865169b1d2057)
BibTeX
@misc{dc293e8788a883,
  title = {Axion 1.0: Open Agent Foundation Models, Simplified — arXiv:2611.03233},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.03233},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_293e8788a883; sha256 8dd0c807e44d55e14d59a3d0a7074c03bb2290e56d77e7a4de2865169b1d2057},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.03233. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We introduce Axion 1.0, a fully open agent foundation model that combines strong and broad agentic capabilities with a remarkably simple training recipe. Axion 1.0 is trained in only three stages: two lightweight supervised fine-tuning stages followed by reinforcement learning, without dedicated mid-training, direct preference optimization (DPO), or on-policy distillation (OPD). The first SFT stage develops strong self-contained reasoning through model-aware data construction, where we synthesize challenging problems and adversarially strengthen them based on the base model's own successful solution strategies. The second stage extends these capabilities to tool-dependent reasoning through a scalable pipeline for constructing diverse and automatically verifiable tasks grounded in real-world data sources and deterministic computation. Finally, reinforcement learning further strengthens long-horizon reasoning and interaction with external tools and environments. Despite this compact training recipe, Axion 1.0 achieves strong performance across a broad suite of agentic benchmarks and is competitive with leading commercial models on several of them. Equally importantly, Axion 1.0 is open beyond model weights: we release the complete recipe, including data construction, generation, filtering, verification, prompts, and training code, enabling the entire development process to be reproduced and extended. Axion 1.0 demonstrates that strong agent foundation models can be both open and simple, offering a practical and reproducible path toward advancing open agentic intelligence.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.03233 — 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 2026-11-03T10:29:48.628Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).