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

arXiv: https://arxiv.org/abs/2507.11407 · HTML: https://mlsanity.com/paper/2507.11407/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 50 of its 70 references that are in the map.
- First posted on arXiv 15 Jul 2025.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 30 of 50)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://mlsanity.com/paper/2311.12022/) (2023)
- [DAPO: An Open-Source LLM Reinforcement Learning System at Scale](https://mlsanity.com/paper/2503.14476/) (2025)
- [LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://mlsanity.com/paper/2403.07974/) (2024)
- [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024)
- [MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark](https://mlsanity.com/paper/2406.01574/) (2024)
- [Gemma 3 Technical Report](https://mlsanity.com/paper/2503.19786/) (2025)
- [GLU Variants Improve Transformer](https://mlsanity.com/paper/2002.05202/) (2020)
- [LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding](https://mlsanity.com/paper/2308.14508/) (2023)
- [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://mlsanity.com/paper/2406.12045/) (2024)
- [GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints](https://mlsanity.com/paper/2305.13245/) (2023)
- [RULER: What's the Real Context Size of Your Long-Context Language Models?](https://mlsanity.com/paper/2404.06654/) (2024)
- [Instruction-Following Evaluation for Large Language Models](https://mlsanity.com/paper/2311.07911/) (2023)
- [Tulu 3: Pushing Frontiers in Open Language Model Post-Training](https://mlsanity.com/paper/2411.15124/) (2024)
- [SimPO: Simple Preference Optimization with a Reference-Free Reward](https://mlsanity.com/paper/2405.14734/) (2024)
- [On Layer Normalization in the Transformer Architecture](https://mlsanity.com/paper/2002.04745/) (2020)
- [DeepSeek-V3 Technical Report](https://mlsanity.com/paper/2412.19437/) (2024)
- [Phi-4 Technical Report](https://mlsanity.com/paper/2412.08905/) (2024)
- [YaRN: Efficient Context Window Extension of Large Language Models](https://mlsanity.com/paper/2309.00071/) (2023)
- [Jamba: A Hybrid Transformer-Mamba Language Model](https://mlsanity.com/paper/2403.19887/) (2024)
- [Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs](https://mlsanity.com/paper/2503.01307/) (2025)
- [2 OLMo 2 Furious](https://mlsanity.com/paper/2501.00656/) (2024)
- [OLMoE: Open Mixture-of-Experts Language Models](https://mlsanity.com/paper/2409.02060/) (2024)

## Built on by (most cited first, 30 of 32)

- [A Cost-Benefit Analysis of On-Premise Large Language Model Deployment: Breaking Even with Commercial LLM Services](https://mlsanity.com/paper/2509.18101/) (2025)
- [Don't Pass@k: A Bayesian Framework for Large Language Model Evaluation](https://mlsanity.com/paper/2510.04265/) (2025)
- [Test-Time Scaling in Reasoning LLMs: Inference Regimes, Evaluation, and Reproducibility](https://mlsanity.com/paper/2608.04001/) (2026)
- [Are they lovers or friends? Evaluating LLMs' Social Reasoning in English and Korean Dialogues](https://mlsanity.com/paper/2510.19028/) (2025)
- [Korean Canonical Legal Benchmark: Toward Knowledge-Independent Evaluation of LLMs' Legal Reasoning Capabilities](https://mlsanity.com/paper/2512.24572/) (2025)
- [FunPRM: Function-as-Step Process Reward Model with Meta Reward Correction for Code Generation](https://mlsanity.com/paper/2601.22249/) (2026)
- [Fast, Slow, and Tool-augmented Thinking for LLMs: A Review](https://mlsanity.com/paper/2508.12265/) (2025)
- [In Their Own Words: Reasoning Traces Tailored for Small Models Make Them Better Reasoners](https://mlsanity.com/paper/2509.22230/) (2025)
- [Everyday Physics in Korean Contexts: A Culturally Grounded Physical Reasoning Benchmark](https://mlsanity.com/paper/2509.17807/) (2025)
- [Future Policy Approximation for Offline Reinforcement Learning in LLM Reasoning](https://mlsanity.com/paper/2509.19893/) (2025)
- [RegexPSPACE: A Benchmark for Evaluating LLM Reasoning on PSPACE-complete Regex Problems](https://mlsanity.com/paper/2510.09227/) (2025)
- [Ranking Reasoning LLMs under Test-Time Scaling](https://mlsanity.com/paper/2603.10960/) (2026)
- [EXAONE 4.5 Technical Report](https://mlsanity.com/paper/2604.08644/) (2026)
- [Pushing the Boundaries of Multiple Choice Evaluation to One Hundred Options](https://mlsanity.com/paper/2604.14634/) (2026)
- [K-FinHallu: A Hallucination Detection Benchmark for Multi-Turn RAG in Korean Finance](https://mlsanity.com/paper/2605.29523/) (2026)
- [Polar: A Benchmark for Evaluating Political Bias in LLMs](https://mlsanity.com/paper/2606.12922/) (2026)
- [Ko-PIQA: A Korean Physical Commonsense Reasoning Dataset with Cultural Context](https://mlsanity.com/paper/2509.11303/) (2025)
- [Beyond Line-Level Filtering for the Pretraining Corpora of LLMs](https://mlsanity.com/paper/2510.24139/) (2025)
- [Ko-MuSR: A Multistep Soft Reasoning Benchmark for LLMs Capable of Understanding Korean](https://mlsanity.com/paper/2510.24150/) (2025)
- [HyperCLOVA X 32B Think](https://mlsanity.com/paper/2601.03286/) (2026)
- [Thunder-KoNUBench: A Corpus-Aligned Benchmark for Korean Negation Understanding](https://mlsanity.com/paper/2601.04693/) (2026)
- [K-MetBench: A Multi-Dimensional Benchmark for Fine-Grained Evaluation of Expert Reasoning, Locality, and Multimodality in Meteorology](https://mlsanity.com/paper/2604.24645/) (2026)
- [Diagnosing Korean-Language LLM Political Bias via Census-Grounded Agent Simulation](https://mlsanity.com/paper/2605.18395/) (2026)
- [NOLLI: A Difficulty-Calibrated Puzzle Benchmark for Diagnosing the English-Korean Performance Gap](https://mlsanity.com/paper/2608.04397/) (2026)
- [K-EXAONE 2.0 Technical Report](https://mlsanity.com/paper/2608.04505/) (2026)
- [mzCache: On-Device LLM Memory Management under Multitasking](https://mlsanity.com/paper/2609.01338/) (2026)
- [How Do Language Models Represent and Use Phonological Information for Allomorph Selection?](https://mlsanity.com/paper/2609.04708/) (2026)
- [ThinkFuse: Trajectory-Aware Test-Time Fusion for Small Reasoning Models](https://mlsanity.com/paper/2610.07803/) (2026)
- [Efficiently Learning To Reason or Not to Reason: Root-token Policy Optimization for Adaptive Thinking](https://mlsanity.com/paper/2610.17767/) (2026)
- [DoubtLess: Training-Free Contrastive Decoding for Efficient Reasoning](https://mlsanity.com/paper/2610.18862/) (2026)

## Abstract (arXiv)

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.