mlsanityData to 14 Oct 2026

Efficient Reasoning Models: A Survey

arXiv 2504.10903 ↗First posted 15 Apr 2025cs.CL cs.AIcited by 95

On the map: LLM reasoning → Test-time compute and efficient thinking

Abstract (arXiv)

Reasoning models have demonstrated remarkable progress in solving complex and logic-intensive tasks by generating extended Chain-of-Thoughts (CoTs) prior to arriving at a final answer. Yet, the emergence of this "slow-thinking" paradigm, with numerous tokens generated in sequence, inevitably introduces substantial computational overhead. To this end, it highlights an urgent need for effective acceleration. This survey aims to provide a comprehensive overview of recent advances in efficient reasoning. It categorizes existing works into three key directions: (1) shorter - compressing lengthy CoTs into concise yet effective reasoning chains; (2) smaller - developing compact language models with strong reasoning capabilities through techniques such as knowledge distillation, other model compression techniques, and reinforcement learning; and (3) faster - designing efficient decoding strategies to accelerate inference of reasoning models. A curated collection of papers discussed in this survey is available in our GitHub repository: https://github.com/fscdc/Awesome-Efficient-Reasoning-Models.

Key facts. Cited by 95 papers in the map (data through 14 Oct 2026). Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning. Builds on 157 of its 192 references that are in the map. First posted on arXiv 15 Apr 2025.

Builds on

157 of 192 references.

Closest ancestors · 54

Same direction, newest first

  1. 2025M1: Towards Scalable Test-Time Compute with Mamba Reasoning Models14 Apr
  2. 2025SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning10 Apr
  3. 2025Quantization Hurts Reasoning? An Empirical Study on Quantized Reasoning Models7 Apr
  4. 2025ThinkPrune: Pruning Long Chain-of-Thought of LLMs via Reinforcement Learning2 Apr
  5. 2025A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyond27 Mar
  6. 2025Unlocking Efficient Long-to-Short LLM Reasoning with Model Merging26 Mar
  7. 2025Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models20 Mar
  8. 2025φ-Decoding: Adaptive Foresight Sampling for Balanced Inference-Time Exploration and Exploitation17 Mar
  9. 2025L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning6 Mar
  10. 2025DAST: Difficulty-Adaptive Slow-Thinking for Large Reasoning Models6 Mar
  11. 2025Sampling-Efficient Test-Time Scaling: Self-Estimating the Best-of-N Sampling in Early Decoding3 Mar
  12. 2025How Well do LLMs Compress Their Own Chain-of-Thought? A Token Complexity Approach3 Mar
38 more
  1. 2025Thinking Slow, Fast: Scaling Inference Compute with Distilled Reasoners27 Feb
  2. 2025Self-Training Elicits Concise Reasoning in Large Language Models27 Feb
  3. 2025Meta-Reasoner: Dynamic Guidance for Optimized Inference-time Reasoning in Large Language Models27 Feb
  4. 2025Efficient Test-Time Scaling via Self-Calibration25 Feb
  5. 2025Towards Thinking-Optimal Scaling of Test-Time Compute for LLM Reasoning25 Feb
  6. 2025Reasoning with Latent Thoughts: On the Power of Looped Transformers24 Feb
  7. 2025Dynamic Parallel Tree Search for Efficient LLM Reasoning22 Feb
  8. 2025LightThinker: Thinking Step-by-Step Compression21 Feb
  9. 2025Inference-Time Computations for LLM Reasoning and Planning: A Benchmark and Insights18 Feb
  10. 2025Revisiting the Test-Time Scaling of o1-like Models: Do they Truly Possess Test-Time Scaling Capabilities?17 Feb
  11. 2025TokenSkip: Controllable Chain-of-Thought Compression in LLMs17 Feb
  12. 2025Atom of Thoughts for Markov LLM Test-Time Scaling17 Feb
  13. 2025FastMCTS: A Simple Sampling Strategy for Data Synthesis17 Feb
  14. 2025Don't Get Lost in the Trees: Streamlining LLM Reasoning by Overcoming Tree Search Exploration Pitfalls16 Feb
  15. 2025CoT-Valve: Length-Compressible Chain-of-Thought Tuning13 Feb
  16. 2025The Danger of Overthinking: Examining the Reasoning-Action Dilemma in Agentic Tasks12 Feb
  17. 2025Bag of Tricks for Inference-time Computation of LLM Reasoning11 Feb
  18. 2025Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling10 Feb
  19. 2025Confidence Improves Self-Consistency in LLMs10 Feb
  20. 2025Token Assorted: Mixing Latent and Text Tokens for Improved Language Model Reasoning5 Feb
  21. 2025Bridging Internal Probability and Self-Consistency for Effective and Efficient LLM Reasoning1 Feb
  22. 2025s1: Simple test-time scaling31 Jan
  23. 2025Reward-Guided Speculative Decoding for Efficient LLM Reasoning31 Jan
  24. 2025Efficient Reasoning with Hidden Thinking31 Jan
  25. 2025Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs30 Jan
  26. 2025O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning22 Jan
  27. 2024Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs30 Dec
  28. 2024Token-Budget-Aware LLM Reasoning24 Dec
  29. 2024Compressed Chain of Thought: Efficient Reasoning Through Dense Representations17 Dec
  30. 2024C3oT: Generating Shorter Chain-of-Thought without Compromising Effectiveness16 Dec
  31. 2024Reasoning Aware Self-Consistency: Leveraging Reasoning Paths for Efficient LLM Sampling30 Aug
  32. 2024Path-Consistency with Prefix Enhancement for Efficient Inference in LLMs25 Aug
  33. 2024Make Every Penny Count: Difficulty-Adaptive Self-Consistency for Cost-Efficient Reasoning24 Aug
  34. 2024Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters6 Aug
  35. 2024Meta Reasoning for Large Language Models17 Jun
  36. 2024Small Language Models Need Strong Verifiers to Self-Correct Reasoning26 Apr
  37. 2024Escape Sky-high Cost: Early-stopping Self-Consistency for Multi-step Reasoning19 Jan
  38. 2023Skeleton-of-Thought: Prompting LLMs for Efficient Parallel Generation28 Jul

50 newest of 54 All 54 (JSON)

Other references · 103

  1. 2022Training language models to follow instructions with human feedbackcited by 15,971
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  3. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  4. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  5. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  6. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  7. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  8. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,371
  9. 2024Qwen2.5 Technical Reportcited by 4,942
  10. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,718
  11. 2017Neural Discrete Representation Learningcited by 4,712
  12. 2023Let's Verify Step by Stepcited by 3,789
38 more
  1. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  2. 2025DAPO: An Open-Source LLM Reinforcement Learning System at Scalecited by 2,810
  3. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,724
  4. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,329
  5. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,242
  6. 2022GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformerscited by 1,919
  7. 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Modelscited by 1,407
  8. 2024τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domainscited by 1,402
  9. 2022SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Modelscited by 1,386
  10. 2025Kimi k1.5: Scaling Reinforcement Learning with LLMscited by 1,210
  11. 2022Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Taskscited by 1,076
  12. 2023Teaching Large Language Models to Self-Debugcited by 988
  13. 2023Graph of Thoughts: Solving Elaborate Problems with Large Language Modelscited by 886
  14. 2024Training Large Language Models to Reason in a Continuous Latent Spacecited by 797
  15. 2021Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategiescited by 743
  16. 2023MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Modelscited by 735
  17. 2024RouteLLM: Learning to Route LLMs with Preference Datacited by 682
  18. 2017Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problemscited by 650
  19. 2023LLM-Pruner: On the Structural Pruning of Large Language Modelscited by 650
  20. 2023WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instructcited by 625
  21. 2019Quantifying the Carbon Emissions of Machine Learningcited by 521
  22. 2025SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wildcited by 511
  23. 2025LIMO: Less is More for Reasoningcited by 498
  24. 2025Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attentioncited by 407
  25. 2025Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Modelscited by 384
  26. 2022Language Models Are Greedy Reasoners: A Systematic Formal Analysis of Chain-of-Thoughtcited by 337
  27. 2023On the Planning Abilities of Large Language Models : A Critical Investigationcited by 312
  28. 2025Chain of Draft: Thinking Faster by Writing Lesscited by 297
  29. 2025Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Modelscited by 293
  30. 2023A Survey on Multimodal Large Language Models for Autonomous Drivingcited by 290
  31. 2022Teaching Small Language Models to Reasoncited by 284
  32. 2024To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoningcited by 263
  33. 2021A Survey of Embodied AI: From Simulators to Research Taskscited by 261
  34. 2024Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunitiescited by 254
  35. 2025Training Language Models to Reason Efficientlycited by 247
  36. 2023Looped Transformers as Programmable Computerscited by 237
  37. 2024From Explicit CoT to Implicit CoT: Learning to Internalize CoT Step by Stepcited by 235
  38. 2025CODI: Compressing Chain-of-Thought into Continuous Space via Self-Distillationcited by 225

50 most cited of 103 All 103 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 55; 2026: 40.

95 papers.

Sort:

By area:

  1. 2025A Survey of Reinforcement Learning for Large Reasoning Modelscited by 180
  2. 2025Thinkless: LLM Learns When to Thinkcited by 113
  3. 2025Think Silently, Think Fast: Dynamic Latent Compression of LLM Reasoning Chainscited by 85
  4. 2025Pangu Embedded: An Efficient Dual-system LLM Reasoner with Metacognitioncited by 62
  5. 2025SSR: Enhancing Depth Perception in Vision-Language Models via Rationale-Guided Spatial Reasoningcited by 46
  6. 2025Implicit Reasoning in Large Language Models: A Comprehensive Surveycited by 43
  7. 2025Don't Overthink It: A Survey of Efficient R1-style Large Reasoning Modelscited by 37
  8. 2025Prolonged Reasoning Is Not All You Need: Certainty-Based Adaptive Routing for Efficient LLM/MLLM Reasoningcited by 35
  9. 2025ConCISE: Confidence-guided Compression in Step-by-step Efficient Reasoningcited by 33
  10. 2025Semantic-Aware Logical Reasoning via a Semiotic Frameworkcited by 32
  11. 2025PixelThink: Towards Efficient Chain-of-Pixel Reasoningcited by 28
  12. 2025A Survey of Token Compression for Efficient Multimodal Large Language Modelscited by 25
38 more
  1. 2025A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Modelscited by 25
  2. 2026LVOmniBench: Pioneering Long Audio-Video Understanding Evaluation for Omnimodal LLMscited by 24
  3. 2025OmniZip: Audio-Guided Dynamic Token Compression for Fast Omnimodal Large Language Modelscited by 22
  4. 2025RewardMap: Tackling Sparse Rewards in Fine-grained Visual Reasoning via Multi-Stage Reinforcement Learningcited by 21
  5. 2025SofT-GRPO: Surpassing Discrete-Token LLM Reinforcement Learning via Gumbel-Reparameterized Soft-Thinking Policy Optimizationcited by 21
  6. 2026Learning to Self-Verify Makes Language Models Better Reasonerscited by 21
  7. 2025Thinking Fast and Right: Balancing Accuracy and Reasoning Length with Adaptive Rewardscited by 20
  8. 2025Early Stopping Chain-of-thoughts in Large Language Modelscited by 20
  9. 2025OBS-Diff: Accurate Pruning For Diffusion Models in One-Shotcited by 19
  10. 2025The Price of a Second Thought: On the Evaluation of Reasoning Efficiency in Large Language Modelscited by 18
  11. 2025Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Trainingcited by 16
  12. 2025Latent Chain-of-Thought World Modeling for End-to-End Drivingcited by 15
  13. 2025Aware First, Think Less: Dynamic Boundary Self-Awareness Drives Extreme Reasoning Efficiency in Large Language Modelscited by 13
  14. 2025FastMTP: Accelerating LLM Inference with Enhanced Multi-Token Predictioncited by 13
  15. 2025Leash: Adaptive Length Penalty and Reward Shaping for Efficient Large Reasoning Modelcited by 13
  16. 2025Active Perception Agent for Omnimodal Audio-Video Understandingcited by 13
  17. 2026Bridging the Gap Between Latent and Explicit Reasoning with Looped Transformerscited by 13
  18. 2025SABER: Switchable and Balanced Training for Efficient LLM Reasoningcited by 12
  19. 2025Retrieval-of-Thought: Efficient Reasoning via Reusing Thoughtscited by 12
  20. 2025ThinkDial: An Open Recipe for Controlling Reasoning Effort in Large Language Modelscited by 11
  21. 2025ConciseHint: Boosting Efficient Reasoning via Continuous Concise Hints during Generationcited by 10
  22. 2025Your Models Have Thought Enough: Training Large Reasoning Models to Stop Overthinkingcited by 10
  23. 2025Revisiting Test-Time Scaling: A Survey and a Diversity-Aware Method for Efficient Reasoningcited by 9
  24. 2026Are Latent Reasoning Models Easily Interpretable?cited by 9
  25. 2025Exploring and Exploiting the Inherent Efficiency within Large Reasoning Models for Self-Guided Efficiency Enhancementcited by 8
  26. 2025Schoenfeld's Anatomy of Mathematical Reasoning by Language Modelscited by 8
  27. 2026Make Geometry Matter for Spatial Reasoningcited by 8
  28. 2025ERC-SVD: Error-Controlled SVD for Large Language Model Compressioncited by 7
  29. 2026Tackling Length Inflation Without Trade-offs: Group Relative Reward Rescaling for Reinforcement Learningcited by 7
  30. 2025Think Before You Prune: Self-Reflective Structured Pruning for Reasoning Language Modelscited by 6
  31. 2026Latent Chain-of-Thought as Planning: Decoupling Reasoning from Verbalizationcited by 6
  32. 2026LongFlow: Efficient KV Cache Compression for Reasoning Modelscited by 6
  33. 2026When Is Thinking Enough? Early Exit via Sufficiency Assessment for Efficient Reasoningcited by 6
  34. 2026From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AIcited by 6
  35. 2025CrossHOI-Bench: A Unified Benchmark for HOI Evaluation across Vision-Language Models and HOI-Specific Methodscited by 5
  36. 2025Learning to Ponder: Adaptive Reasoning in Latent Spacecited by 5
  37. 2025EffiReasonTrans: RL-Optimized Reasoning for Code Translationcited by 5
  38. 2026Seeing Through the Chain: Mitigate Hallucination in Multimodal Reasoning Models via CoT Compression and Contrastive Preference Optimizationcited by 5

50 most cited of 95 All 95 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Efficient Inference for Large Reasoning Models: A Survey
  2. 2025Can Reasoning Path still be Effective as Input? Bridging Post-Reasoning to Chain-of-Thought Compression
  3. 2026Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compression
  4. 2025Towards Concise and Adaptive Thinking in Large Reasoning Models: A Survey
  5. 2025Harnessing the Reasoning Economy: A Survey of Efficient Reasoning for Large Language Models
  6. 2025Efficient Reasoning via Thought-Training and Thought-Free Inference
  7. 2025Reasoning Beyond Language: A Comprehensive Survey on Latent Chain-of-Thought Reasoning
  8. 2025Dynamic Early Exit in Reasoning Models