_version_ 1866917179372339200
author Bae, Kyunghoon
Choi, Eunbi
Choi, Kibong
Choi, Stanley Jungkyu
Choi, Yemuk
Han, Kyubeen
Hong, Seokhee
Hwang, Junwon
Hwang, Taewan
Jang, Joonwon
Jeon, Hyojin
Jeon, Kijeong
Jo, Gerrard Jeongwon
Jo, Hyunjik
Jung, Jiyeon
Kim, Euisoon
Kim, Hyosang
Kim, Jihoon
Kim, Joonkee
Kim, Seonghwan
Kim, Soyeon
Kim, Sunkyoung
Kim, Yireun
Kim, Yongil
Kim, Youchul
Lee, Edward Hwayoung
Lee, Gwangho
Lee, Haeju
Lee, Honglak
Lee, Jinsik
Lee, Kyungmin
Park, Sangha
Paik, Young Min
Park, Yongmin
Park, Youngyong
Seo, Sanghyun
Yang, Sihoon
Yeen, Heuiyeen
Yi, Sihyuk
Yun, Hyeongu
author_facet Bae, Kyunghoon
Choi, Eunbi
Choi, Kibong
Choi, Stanley Jungkyu
Choi, Yemuk
Han, Kyubeen
Hong, Seokhee
Hwang, Junwon
Hwang, Taewan
Jang, Joonwon
Jeon, Hyojin
Jeon, Kijeong
Jo, Gerrard Jeongwon
Jo, Hyunjik
Jung, Jiyeon
Kim, Euisoon
Kim, Hyosang
Kim, Jihoon
Kim, Joonkee
Kim, Seonghwan
Kim, Soyeon
Kim, Sunkyoung
Kim, Yireun
Kim, Yongil
Kim, Youchul
Lee, Edward Hwayoung
Lee, Gwangho
Lee, Haeju
Lee, Honglak
Lee, Jinsik
Lee, Kyungmin
Park, Sangha
Paik, Young Min
Park, Yongmin
Park, Youngyong
Seo, Sanghyun
Yang, Sihoon
Yeen, Heuiyeen
Yi, Sihyuk
Yun, Hyeongu
contents This technical report introduces EXAONE 4.0, which integrates a Non-reasoning mode and a Reasoning mode to achieve both the excellent usability of EXAONE 3.5 and the advanced reasoning abilities of EXAONE Deep. To pave the way for the agentic AI era, EXAONE 4.0 incorporates essential features such as agentic tool use, and its multilingual capabilities are extended to support Spanish in addition to English and Korean. The EXAONE 4.0 model series consists of two sizes: a mid-size 32B model optimized for high performance, and a small-size 1.2B model designed for on-device applications. The EXAONE 4.0 demonstrates superior performance compared to open-weight models in its class and remains competitive even against frontier-class models. The models are publicly available for research purposes and can be easily downloaded via https://huggingface.co/LGAI-EXAONE.
format Preprint
id arxiv_https___arxiv_org_abs_2507_11407
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle EXAONE 4.0: Unified Large Language Models Integrating Non-reasoning and Reasoning Modes
Bae, Kyunghoon
Choi, Eunbi
Choi, Kibong
Choi, Stanley Jungkyu
Choi, Yemuk
Han, Kyubeen
Hong, Seokhee
Hwang, Junwon
Hwang, Taewan
Jang, Joonwon
Jeon, Hyojin
Jeon, Kijeong
Jo, Gerrard Jeongwon
Jo, Hyunjik
Jung, Jiyeon
Kim, Euisoon
Kim, Hyosang
Kim, Jihoon
Kim, Joonkee
Kim, Seonghwan
Kim, Soyeon
Kim, Sunkyoung
Kim, Yireun
Kim, Yongil
Kim, Youchul
Lee, Edward Hwayoung
Lee, Gwangho
Lee, Haeju
Lee, Honglak
Lee, Jinsik
Lee, Kyungmin
Park, Sangha
Paik, Young Min
Park, Yongmin
Park, Youngyong
Seo, Sanghyun
Yang, Sihoon
Yeen, Heuiyeen
Yi, Sihyuk
Yun, Hyeongu
Computation and Language
Artificial Intelligence
This technical report introduces EXAONE 4.0, which integrates a Non-reasoning mode and a Reasoning mode to achieve both the excellent usability of EXAONE 3.5 and the advanced reasoning abilities of EXAONE Deep. To pave the way for the agentic AI era, EXAONE 4.0 incorporates essential features such as agentic tool use, and its multilingual capabilities are extended to support Spanish in addition to English and Korean. The EXAONE 4.0 model series consists of two sizes: a mid-size 32B model optimized for high performance, and a small-size 1.2B model designed for on-device applications. The EXAONE 4.0 demonstrates superior performance compared to open-weight models in its class and remains competitive even against frontier-class models. The models are publicly available for research purposes and can be easily downloaded via https://huggingface.co/LGAI-EXAONE.
title EXAONE 4.0: Unified Large Language Models Integrating Non-reasoning and Reasoning Modes
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2507.11407