K-EXAONE 2.0 技术报告

摘要

本技术报告介绍K-EXAONE 2.0，这是由LG AI研究开发的一个开放权重多语言基础模型，是我们迈向全球前沿规模基础模型征程中的一步。我们没有从头开始训练，而是对K-EXAONE进行升级改造并扩展其架构，形成了一个总参数量为750B、每个令牌激活约37B参数的混合专家（MoE）模型——其容量是前代模型的三倍以上。K-EXAONE 2.0支持高达256K令牌的上下文长度，并将多语言覆盖范围从六种语言扩展到十种语言。其训练流程结合了持续预训练、聚焦难度的中期训练和后期训练，以强化推理能力、智能体编码能力、多语言能力以及基于韩国社会文化语境的安全性。在九个为反映实际使用条件而选取的评估类别中，K-EXAONE 2.0相较于K-EXAONE有所提升，并与开放权重模型保持竞争力，其在智能体编码和长上下文理解方面提升最大，在长上下文检索和安全性方面优势最为突出。K-EXAONE 2.0在Apache 2.0许可证下发布，使更广泛的人工智能生态能够对其进行评估、部署、适配和二次开发，同时标志着我们挑战全球前沿的开始——而非终点。

English

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.