mlsanityData to 7 Oct 2026

From System 1 to System 2: A Survey of Reasoning Large Language Models

arXiv 2502.17419 ↗First posted 24 Feb 2025cs.AIcited by 319

On the map: LLM reasoning → Reasoning benchmarks and evaluation

Abstract (arXiv)

Achieving human-level intelligence requires refining the transition from the fast, intuitive System 1 to the slower, more deliberate System 2 reasoning. While System 1 excels in quick, heuristic decisions, System 2 relies on logical reasoning for more accurate judgments and reduced biases. Foundational Large Language Models (LLMs) excel at fast decision-making but lack the depth for complex reasoning, as they have not yet fully embraced the step-by-step analysis characteristic of true System 2 thinking. Recently, reasoning LLMs like OpenAI's o1/o3 and DeepSeek's R1 have demonstrated expert-level performance in fields such as mathematics and coding, closely mimicking the deliberate reasoning of System 2 and showcasing human-like cognitive abilities. This survey begins with a brief overview of the progress in foundational LLMs and the early development of System 2 technologies, exploring how their combination has paved the way for reasoning LLMs. Next, we discuss how to construct reasoning LLMs, analyzing their features, the core methods enabling advanced reasoning, and the evolution of various reasoning LLMs. Additionally, we provide an overview of reasoning benchmarks, offering an in-depth comparison of the performance of representative reasoning LLMs. Finally, we explore promising directions for advancing reasoning LLMs and maintain a real-time hrefhttps://github.com/zzli2022/Awesome-Slow-Reason-SystemGitHub Repository to track the latest developments. We hope this survey will serve as a valuable resource to inspire innovation and drive progress in this rapidly evolving field.

Key facts. Cited by 319 papers in the map (data through 7 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 323 of its 549 references that are in the map. First posted on arXiv 24 Feb 2025.

Builds on

323 of 549 references.

Closest ancestors · 17

Same direction, newest first

  1. 2025ThinkBench: Dynamic Out-of-Distribution Evaluation for Robust LLM Reasoning22 Feb
  2. 2025EnigmaEval: A Benchmark of Long Multimodal Reasoning Challenges13 Feb
  3. 2025ZebraLogic: On the Scaling Limits of LLMs for Logical Reasoning3 Feb
  4. 2025JustLogic: A Comprehensive Benchmark for Evaluating Deductive Reasoning in Large Language Models24 Jan
  5. 2025Reasoning Language Models: A Blueprint20 Jan
  6. 2025Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models16 Jan
  7. 2024Beyond Examples: High-level Automated Reasoning Paradigm in In-Context Learning via MCTS27 Nov
  8. 2024Mutual Reasoning Makes Smaller LLMs Stronger Problem-Solvers12 Aug
  9. 2024MR-Ben: A Meta-Reasoning Benchmark for Evaluating System-2 Thinking in LLMs20 Jun
  10. 2024AutoPSV: Automated Process-Supervised Verifier27 May
  11. 2024Can LLMs Learn from Previous Mistakes? Investigating LLMs' Errors to Boost for Reasoning29 Mar
  12. 2024Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking14 Mar
5 more
  1. 2023LLaMA: Open and Efficient Foundation Language Models27 Feb
  2. 2022Towards Reasoning in Large Language Models: A Survey20 Dec
  3. 2022PAL: Program-aided Language Models18 Nov
  4. 2022Making Large Language Models Better Reasoners with Step-Aware Verifier6 Jun
  5. 2022Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?25 Feb

Other references · 306

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  4. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  5. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  6. 2020Language Models are Few-Shot Learnerscited by 32,199
  7. 2023GPT-4 Technical Reportcited by 18,132
  8. 2022Training language models to follow instructions with human feedbackcited by 15,712
  9. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  10. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  11. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  12. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
38 more
  1. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  2. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  3. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  4. 2023Visual Instruction Tuningcited by 7,792
  5. 2016Densely Connected Convolutional Networkscited by 6,691
  6. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,146
  7. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,069
  8. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,767
  9. 2022Generative Adversarial Networkscited by 5,603
  10. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  11. 2025Qwen2.5-VL Technical Reportcited by 5,418
  12. 2024Qwen2.5 Technical Reportcited by 4,713
  13. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,616
  14. 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 4,337
  15. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  16. 2021Zero-Shot Text-to-Image Generationcited by 4,276
  17. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,769
  18. 2023Let's Verify Step by Stepcited by 3,598
  19. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,317
  20. 2023SWE-bench: Can Language Models Resolve Real-World GitHub Issues?cited by 3,193
  21. 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,175
  22. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,155
  23. 2014Sequence to Sequence Learning with Neural Networkscited by 2,974
  24. 2023InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuningcited by 2,855
  25. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,748
  26. 2023A Survey of Large Language Modelscited by 2,537
  27. 2023MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGIcited by 2,044
  28. 2023WebArena: A Realistic Web Environment for Building Autonomous Agentscited by 1,908
  29. 2024LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Codecited by 1,906
  30. 2022Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answeringcited by 1,881
  31. 2019Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelismcited by 1,829
  32. 2022Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Themcited by 1,767
  33. 2024MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmarkcited by 1,758
  34. 2022Fast Inference from Transformers via Speculative Decodingcited by 1,615
  35. 2023MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contextscited by 1,582
  36. 2022Competition-Level Code Generation with AlphaCodecited by 1,427
  37. 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Modelscited by 1,397
  38. 2020What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Examscited by 1,324

50 most cited of 306 All 306 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 209; 2026: 110.

319 papers.

Sort:

By area:

  1. 2025Video-R1: Reinforcing Video Reasoning in MLLMscited by 464
  2. 2025Stop Overthinking: A Survey on Efficient Reasoning for Large Language Modelscited by 456
  3. 2025Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Modelscited by 381
  4. 2025WebThinker: Empowering Large Reasoning Models with Deep Research Capabilitycited by 320
  5. 2025The Landscape of Agentic Reinforcement Learning for LLMs: A Surveycited by 195
  6. 2025Multimodal Chain-of-Thought Reasoning: A Comprehensive Surveycited by 176
  7. 2025A Survey of Reinforcement Learning for Large Reasoning Modelscited by 175
  8. 2025ShieldAgent: Shielding Agents via Verifiable Safety Policy Reasoningcited by 144
  9. 2025Between Underthinking and Overthinking: An Empirical Study of Reasoning Length and correctness in LLMscited by 115
  10. 2025A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deploymentcited by 110
  11. 2025Agentic Large Language Models, a surveycited by 105
  12. 2025MedReason: Eliciting Factual Medical Reasoning Steps in LLMs via Knowledge Graphscited by 105
38 more
  1. 2025DeepSeek-R1 Thoughtology: Let's think about LLM Reasoningcited by 91
  2. 2025A Sober Look at Progress in Language Model Reasoning: Pitfalls and Paths to Reproducibilitycited by 89
  3. 2025ShorterBetter: Guiding Reasoning Models to Find Optimal Inference Length for Efficient Reasoningcited by 70
  4. 2025LifelongAgentBench: Evaluating LLM Agents as Lifelong Learnerscited by 65
  5. 2025FlowReasoner: Reinforcing Query-Level Meta-Agentscited by 56
  6. 2025Beyond Pass@1: Self-Play with Variational Problem Synthesis Sustains RLVRcited by 53
  7. 2025PolyMath: Evaluating Mathematical Reasoning in Multilingual Contextscited by 52
  8. 2025A Survey on Large Language Models for Mathematical Reasoningcited by 52
  9. 2025Speculative Thinking: Enhancing Small-Model Reasoning with Large Model Guidance at Inference Timecited by 48
  10. 2025Implicit Reasoning in Large Language Models: A Comprehensive Surveycited by 42
  11. 2025Latent Sketchpad: Sketching Visual Thoughts to Elicit Multimodal Reasoning in MLLMscited by 41
  12. 2025SwS: Self-aware Weakness-driven Problem Synthesis in Reinforcement Learning for LLM Reasoningcited by 39
  13. 2025ARM: Adaptive Reasoning Modelcited by 38
  14. 2025ThinkSwitcher: When to Think Hard, When to Think Fastcited by 37
  15. 2025MMR1: Enhancing Multimodal Reasoning with Variance-Aware Sampling and Open Resourcescited by 37
  16. 2025Don't Overthink It: A Survey of Efficient R1-style Large Reasoning Modelscited by 36
  17. 2025Harnessing the Reasoning Economy: A Survey of Efficient Reasoning for Large Language Modelscited by 35
  18. 2025Learning to Reason for Long-Form Story Generationcited by 34
  19. 2025MM-CoT:A Benchmark for Probing Visual Chain-of-Thought Reasoning in Multimodal Modelscited by 33
  20. 2025Think or Not? Exploring Thinking Efficiency in Large Reasoning Models via an Information-Theoretic Lenscited by 32
  21. 2025NewtonBench: Benchmarking Generalizable Scientific Law Discovery in LLM Agentscited by 32
  22. 2025Multimodal Spatial Reasoning in the Large Model Era: A Survey and Benchmarkscited by 31
  23. 2025Orak: A Foundational Benchmark for Training and Evaluating LLM Agents on Diverse Video Gamescited by 30
  24. 2025Energy-Based Transformers are Scalable Learners and Thinkerscited by 30
  25. 2025R1-Compress: Long Chain-of-Thought Compression via Chunk Compression and Searchcited by 29
  26. 2025AutoReproduce: Automatic AI Experiment Reproduction with Paper Lineagecited by 29
  27. 2025PixelThink: Towards Efficient Chain-of-Pixel Reasoningcited by 28
  28. 2025From Perception to Cognition: A Survey of Vision-Language Interactive Reasoning in Multimodal Large Language Modelscited by 26
  29. 2025Mitigating Deceptive Alignment via Self-Monitoringcited by 25
  30. 2025GRAM: A Generative Foundation Reward Model for Reward Generalizationcited by 25
  31. 2025LaDiR: Latent Diffusion Enhances LLMs for Text Reasoningcited by 25
  32. 2025Genius: A Generalizable and Purely Unsupervised Self-Training Framework For Advanced Reasoningcited by 24
  33. 2025OpenCodeReasoning-II: A Simple Test Time Scaling Approach via Self-Critiquecited by 24
  34. 2025RECODE-H: A Benchmark for Research Code Development with Interactive Human Feedbackcited by 24
  35. 2025System-1.5 Reasoning: Traversal in Language and Latent Spaces with Dynamic Shortcutscited by 23
  36. 2025Route to Reason: Adaptive Routing for LLM and Reasoning Strategy Selectioncited by 23
  37. 2025Scaling and Beyond: Advancing Spatial Reasoning in MLLMs Requires New Recipescited by 22
  38. 2026Why Reasoning Fails to Plan: A Planning-Centric Analysis of Long-Horizon Decision Making in LLM Agentscited by 22

50 most cited of 319 All 319 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Reasoning on a Spectrum: Aligning LLMs to System 1 and System 2 Thinking
  2. 2025Human-Level Reasoning: A Comparative Study of Large Language Models on Logical and Abstract Reasoning
  3. 2025Logical Reasoning in Large Language Models: A Survey
  4. 2024Beyond Accuracy: Evaluating the Reasoning Behavior of Large Language Models -- A Survey
  5. 2024LLM2: Let Large Language Models Harness System 2 Reasoning
  6. 2025Advancing Reasoning in Large Language Models: Promising Methods and Approaches
  7. 2026Mathematical Reasoning in Large Language Models: Benchmarks, Architectures, Evaluation, and Open Challenges
  8. 2025Thinking Machines: A Survey of LLM based Reasoning Strategies