Metraipolis › archive › dc_11b3879d8f4e

K-EXAONE 2.0 Technical Report — arXiv:2608.04505

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.04505
License (as archived)
CC0-1.0
Archived
2026-10-31T11:24:40.027Z
SHA-256 of the archived text
9b163aa69e7be147daedf361190fa0a86ba5b0b6abbc41137ac8d9b0546b07e6
Stable URL of this page
https://metraipolis.com/documento/dc_11b3879d8f4e

How to cite

K-EXAONE 2.0 Technical Report — arXiv:2608.04505 — arXiv (en), https://arxiv.org/abs/2608.04505 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_11b3879d8f4e (Metraipolis archive dc_11b3879d8f4e, sha256 9b163aa69e7be147daedf361190fa0a86ba5b0b6abbc41137ac8d9b0546b07e6)
BibTeX
@misc{dc11b3879d8f4e,
  title = {K-EXAONE 2.0 Technical Report — arXiv:2608.04505},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.04505},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_11b3879d8f4e; sha256 9b163aa69e7be147daedf361190fa0a86ba5b0b6abbc41137ac8d9b0546b07e6},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.04505. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

This technical report presents K-EXAONE 2.0, an open-weight multilingual foundation model developed by LG AI Research as a step in our effort toward global frontier-scale foundation models. Rather than training from scratch, we upcycle K-EXAONE and expand its architecture, yielding a Mixture-of-Experts (MoE) model with 750B total parameters and approximately 37B activated per token---more than three times the capacity of its predecessor. K-EXAONE 2.0 supports context lengths of up to 256K tokens and expands multilingual coverage from six to ten languages. Its training pipeline combines continual pre-training, difficulty-focused mid-training, and post-training to strengthen reasoning, agentic coding, multilingual capability, and safety grounded in Korean sociocultural contexts. Across nine evaluation categories selected to reflect the conditions of practical use, K-EXAONE 2.0 improves over K-EXAONE and remains competitive with open-weight models, showing its largest gains in agentic coding and long-context understanding and its clearest strengths in long-context retrieval and safety. Released under the Apache 2.0 license, K-EXAONE 2.0 enables the wider AI ecosystem to evaluate, deploy, adapt, and build upon it, while marking the beginning---rather than the endpoint---of our challenge toward the global frontier.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-06 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2608.04505 — 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 2026-10-31T11:13:23.171Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-06?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).