mlsanityData to 14 Oct 2026

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

arXiv 2507.11407 ↗First posted 15 Jul 2025cs.CL cs.AIcited by 32

On the map: LLM reasoning → Reasoning benchmarks and evaluation

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.

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.

Builds on

50 of 70 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025Skywork Open Reasoner 1 Technical Report28 May
  2. 2025Qwen3 Technical Report14 May
  3. 2025Phi-4-reasoning Technical Report30 Apr
  4. 2024DeepSeek-V3 Technical Report27 Dec

Other references · 46

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  3. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  4. 2020Measuring Massive Multitask Language Understandingcited by 7,963
  5. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  6. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,703
  7. 2023Let's Verify Step by Stepcited by 3,789
  8. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,879
  9. 2025DAPO: An Open-Source LLM Reinforcement Learning System at Scalecited by 2,810
  10. 2024LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Codecited by 2,004
  11. 2024Gemma 2: Improving Open Language Models at a Practical Sizecited by 1,998
  12. 2024MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmarkcited by 1,848
34 more
  1. 2025Gemma 3 Technical Reportcited by 1,824
  2. 2020GLU Variants Improve Transformercited by 1,804
  3. 2023LongBench: A Bilingual, Multitask Benchmark for Long Context Understandingcited by 1,417
  4. 2024τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domainscited by 1,402
  5. 2023GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpointscited by 1,346
  6. 2024RULER: What's the Real Context Size of Your Long-Context Language Models?cited by 1,346
  7. 2023Instruction-Following Evaluation for Large Language Modelscited by 1,228
  8. 2024Tulu 3: Pushing Frontiers in Open Language Model Post-Trainingcited by 1,053
  9. 2024SimPO: Simple Preference Optimization with a Reference-Free Rewardcited by 963
  10. 2020On Layer Normalization in the Transformer Architecturecited by 922
  11. 2024Phi-4 Technical Reportcited by 711
  12. 2023YaRN: Efficient Context Window Extension of Large Language Modelscited by 601
  13. 2024Jamba: A Hybrid Transformer-Mamba Language Modelcited by 401
  14. 2025Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRscited by 377
  15. 20242 OLMo 2 Furiouscited by 340
  16. 2024OLMoE: Open Mixture-of-Experts Language Modelscited by 301
  17. 2025MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attentioncited by 263
  18. 2024Are We Done with MMLU?cited by 194
  19. 2025MiniMax-01: Scaling Foundation Models with Lightning Attentioncited by 166
  20. 2025The Surprising Effectiveness of Negative Reinforcement in LLM Reasoningcited by 162
  21. 2024HELMET: How to Evaluate Long-Context Language Models Effectively and Thoroughlycited by 125
  22. 2024Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMscited by 108
  23. 2024Multi-IF: Benchmarking LLMs on Multi-Turn and Multilingual Instructions Followingcited by 102
  24. 2025Nemotron-H: A Family of Accurate and Efficient Hybrid Mamba-Transformer Modelscited by 100
  25. 2025WMT24++: Expanding the Language Coverage of WMT24 to 55 Languages & Dialectscited by 79
  26. 2025The Curse of Depth in Large Language Modelscited by 62
  27. 2025Magistralcited by 60
  28. 2024EXAONE 3.5: Series of Large Language Models for Real-world Use Casescited by 53
  29. 2025Rope to Nope and Back Again: A New Hybrid Attention Strategycited by 47
  30. 2025Understand, Solve and Translate: Bridging the Multilingual Mathematical Reasoning Gapcited by 43
  31. 2025On a few pitfalls in KL divergence gradient estimation for RLcited by 29
  32. 2025SimPER: A Minimalist Approach to Preference Alignment without Hyperparameterscited by 25
  33. 2024EXAONE 3.0 7.8B Instruction Tuned Language Modelcited by 21
  34. 2025EXAONE Deep: Reasoning Enhanced Language Modelscited by 21

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 12; 2026: 20.

32 papers.

Sort:

By area:

  1. 2025A Cost-Benefit Analysis of On-Premise Large Language Model Deployment: Breaking Even with Commercial LLM Servicescited by 17
  2. 2025Don't Pass@k: A Bayesian Framework for Large Language Model Evaluationcited by 15
  3. 2026Test-Time Scaling in Reasoning LLMs: Inference Regimes, Evaluation, and Reproducibilitycited by 6
  4. 2025Are they lovers or friends? Evaluating LLMs' Social Reasoning in English and Korean Dialoguescited by 3
  5. 2025Korean Canonical Legal Benchmark: Toward Knowledge-Independent Evaluation of LLMs' Legal Reasoning Capabilitiescited by 3
  6. 2026FunPRM: Function-as-Step Process Reward Model with Meta Reward Correction for Code Generationcited by 3
  7. 2025Fast, Slow, and Tool-augmented Thinking for LLMs: A Reviewcited by 2
  8. 2025In Their Own Words: Reasoning Traces Tailored for Small Models Make Them Better Reasonerscited by 2
  9. 2025Everyday Physics in Korean Contexts: A Culturally Grounded Physical Reasoning Benchmarkcited by 1
  10. 2025Future Policy Approximation for Offline Reinforcement Learning in LLM Reasoningcited by 1
  11. 2025RegexPSPACE: A Benchmark for Evaluating LLM Reasoning on PSPACE-complete Regex Problemscited by 1
  12. 2026Ranking Reasoning LLMs under Test-Time Scalingcited by 1
20 more
  1. 2026EXAONE 4.5 Technical Reportcited by 1
  2. 2026Pushing the Boundaries of Multiple Choice Evaluation to One Hundred Optionscited by 1
  3. 2026K-FinHallu: A Hallucination Detection Benchmark for Multi-Turn RAG in Korean Financecited by 1
  4. 2026Polar: A Benchmark for Evaluating Political Bias in LLMscited by 1
  5. 2025Ko-PIQA: A Korean Physical Commonsense Reasoning Dataset with Cultural Contextcited by 0
  6. 2025Beyond Line-Level Filtering for the Pretraining Corpora of LLMscited by 0
  7. 2025Ko-MuSR: A Multistep Soft Reasoning Benchmark for LLMs Capable of Understanding Koreancited by 0
  8. 2026HyperCLOVA X 32B Thinkcited by 0
  9. 2026Thunder-KoNUBench: A Corpus-Aligned Benchmark for Korean Negation Understandingcited by 0
  10. 2026K-MetBench: A Multi-Dimensional Benchmark for Fine-Grained Evaluation of Expert Reasoning, Locality, and Multimodality in Meteorologycited by 0
  11. 2026Diagnosing Korean-Language LLM Political Bias via Census-Grounded Agent Simulationcited by 0
  12. 2026NOLLI: A Difficulty-Calibrated Puzzle Benchmark for Diagnosing the English-Korean Performance Gapcited by 0
  13. 2026K-EXAONE 2.0 Technical Reportcited by 0
  14. 2026mzCache: On-Device LLM Memory Management under Multitaskingcited by 0
  15. 2026How Do Language Models Represent and Use Phonological Information for Allomorph Selection?cited by 0
  16. 2026ThinkFuse: Trajectory-Aware Test-Time Fusion for Small Reasoning Modelscited by 0
  17. 2026Efficiently Learning To Reason or Not to Reason: Root-token Policy Optimization for Adaptive Thinkingcited by 0
  18. 2026DoubtLess: Training-Free Contrastive Decoding for Efficient Reasoningcited by 0
  19. 2026ixi-sLM: On-Device sLM for AI Call Agent Servicecited by 0
  20. 2026KoAGE: Do Large Language Models Know, Learn, and Coin Korean Neologisms?cited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026K-EXAONE Technical Report
  2. 2024LLMArena: Assessing Capabilities of Large Language Models in Dynamic Multi-Agent Environments
  3. 2025GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models
  4. 2024Large Language Model Evaluation Via Multi AI Agents: Preliminary results
  5. 2025Large Language Models for Agent-Based Modelling: Current and possible uses across the modelling cycle
  6. 2025Large Language Model Agent: A Survey on Methodology, Applications and Challenges
  7. 2023The Rise and Potential of Large Language Model Based Agents: A Survey
  8. 2024SUTRA: Scalable Multilingual Language Model Architecture