a month ago

EXAONE 4.0: Unified Large Language Models Integrating Non-reasoning and Reasoning Modes

LG AI Research, Kyunghoon Bae, Eunbi Choi, Kibong Choi, Stanley Jungkyu Choi, Yemuk Choi, Kyubeen Han, Seokhee Hong, Junwon Hwang, Taewan Hwang, Joonwon Jang, Hyojin Jeon, Kijeong Jeon, Gerrard Jeongwon Jo, Hyunjik Jo, Jiyeon Jung, Euisoon Kim, Hyosang Kim, Jihoon Kim, Joonkee Kim, Seonghwan Kim, Soyeon Kim, Sunkyoung Kim, Yireun Kim, Yongil Kim, Youchul Kim, Edward Hwayoung Lee, Gwangho Lee, Haeju Lee, Honglak Lee, Jinsik Lee, Kyungmin Lee, Sangha Park, Young Min Paik, Yongmin Park, Youngyong Park, Sanghyun Seo, Sihoon Yang, Heuiyeen Yeen, Sihyuk Yi, Hyeongu Yun

View Paper Details

EXAONE 4.0: Unified Large Language Models Integrating Non-reasoning and
Reasoning Modes

Abstract

This technical report introduces EXAONE 4.0, which integrates a Non-reasoningmode and a Reasoning mode to achieve both the excellent usability of EXAONE 3.5and the advanced reasoning abilities of EXAONE Deep. To pave the way for theagentic AI era, EXAONE 4.0 incorporates essential features such as agentic tooluse, and its multilingual capabilities are extended to support Spanish inaddition to English and Korean. The EXAONE 4.0 model series consists of twosizes: a mid-size 32B model optimized for high performance, and a small-size1.2B model designed for on-device applications. The EXAONE 4.0 demonstratessuperior performance compared to open-weight models in its class and remainscompetitive even against frontier-class models. The models are publiclyavailable for research purposes and can be easily downloaded viahttps://huggingface.co/LGAI-EXAONE.