mlsanityData to 14 Oct 2026

A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well?

arXiv 2503.24235 ↗First posted 31 Mar 2025cs.CL cs.AIcited by 223

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

Abstract (arXiv)

As enthusiasm for scaling computation (data and parameters) in the pretraining era gradually diminished, test-time scaling (TTS), also referred to as ``test-time computing'' has emerged as a prominent research focus. Recent studies demonstrate that TTS can further elicit the problem-solving capabilities of large language models (LLMs), enabling significant breakthroughs not only in specialized reasoning tasks, such as mathematics and coding, but also in general tasks like open-ended Q&A. However, despite the explosion of recent efforts in this area, there remains an urgent need for a comprehensive survey offering a systemic understanding. To fill this gap, we propose a unified, multidimensional framework structured along four core dimensions of TTS research: what to scale, how to scale, where to scale, and how well to scale. Building upon this taxonomy, we conduct an extensive review of methods, application scenarios, and assessment aspects, and present an organized decomposition that highlights the unique functional roles of individual techniques within the broader TTS landscape. From this analysis, we distill the major developmental trajectories of TTS to date and offer hands-on guidelines for practical deployment. Furthermore, we identify several open challenges and offer insights into promising future directions, including further scaling, clarifying the functional essence of techniques, generalizing to more tasks, and more attributions. Our repository is available on https://github.com/testtimescaling/testtimescaling.github.io/

Key facts. Cited by 223 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 221 of its 291 references that are in the map. First posted on arXiv 31 Mar 2025.

Builds on

221 of 291 references.

Closest ancestors · 48

Same direction, newest first

  1. 2025A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyond27 Mar
  2. 2025L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning6 Mar
  3. 2025START: Self-taught Reasoner with Tools6 Mar
  4. 2025Wider or Deeper? Scaling LLM Inference-Time Compute with Adaptive Branching Tree Search6 Mar
  5. 2025Efficient Test-Time Scaling via Self-Calibration25 Feb
  6. 2025Scalable Best-of-N Selection for Large Language Models via Self-Certainty25 Feb
  7. 2025Towards Thinking-Optimal Scaling of Test-Time Compute for LLM Reasoning25 Feb
  8. 2025Reasoning with Latent Thoughts: On the Power of Looped Transformers24 Feb
  9. 2025LightThinker: Thinking Step-by-Step Compression21 Feb
  10. 2025ETS: Efficient Tree Search for Inference-Time Scaling19 Feb
  11. 2025Revisiting the Test-Time Scaling of o1-like Models: Do they Truly Possess Test-Time Scaling Capabilities?17 Feb
  12. 2025Atom of Thoughts for Markov LLM Test-Time Scaling17 Feb
36 more
  1. 2025Learning to Reason from Feedback at Test-Time16 Feb
  2. 2025ReasonFlux: Hierarchical LLM Reasoning via Scaling Thought Templates10 Feb
  3. 2025Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling10 Feb
  4. 2025Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach7 Feb
  5. 2025Demystifying Long Chain-of-Thought Reasoning in LLMs5 Feb
  6. 2025Token Assorted: Mixing Latent and Text Tokens for Improved Language Model Reasoning5 Feb
  7. 2025CoAT: Chain-of-Associated-Thoughts Framework for Enhancing Large Language Models Reasoning4 Feb
  8. 2025Latent Thought Models with Variational Bayes Inference-Time Computation3 Feb
  9. 2025s1: Simple test-time scaling31 Jan
  10. 2025Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs30 Jan
  11. 2025Critique Fine-Tuning: Learning to Critique is More Effective than Learning to Imitate29 Jan
  12. 2025From Drafts to Answers: Unlocking LLM Potential via Aggregation Fine-Tuning21 Jan
  13. 2025T1: Advancing Language Model Reasoning through Reinforcement Learning and Inference Scaling20 Jan
  14. 2024Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs30 Dec
  15. 2024Forest-of-Thought: Scaling Test-Time Compute for Enhancing LLM Reasoning12 Dec
  16. 2024Critical Tokens Matter: Token-Level Contrastive Estimation Enhances LLM's Reasoning Capability29 Nov
  17. 2024O1 Replication Journey -- Part 2: Surpassing O1-preview through Simple Distillation, Big Progress or Bitter Lesson?25 Nov
  18. 2024Marco-o1: Towards Open Reasoning Models for Open-Ended Solutions21 Nov
  19. 2024TreeBoN: Enhancing Inference-Time Alignment with Speculative Tree-Search and Best-of-N Sampling18 Oct
  20. 2024A Comparative Study on Reasoning Patterns of OpenAI's o1 Model17 Oct
  21. 2024LLM Self-Correction with DeCRIM: Decompose, Critique, and Refine for Enhanced Following of Instructions with Multiple Constraints9 Oct
  22. 2024O1 Replication Journey: A Strategic Progress Report -- Part 18 Oct
  23. 2024Interpretable Contrastive Monte Carlo Tree Search Reasoning2 Oct
  24. 2024Make Every Penny Count: Difficulty-Adaptive Self-Consistency for Cost-Efficient Reasoning24 Aug
  25. 2024Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters6 Aug
  26. 2024Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for Problem-Solving with Language Models1 Aug
  27. 2024When is the consistent prediction likely to be a correct prediction?8 Jul
  28. 2024Small Language Models Need Strong Verifiers to Self-Correct Reasoning26 Apr
  29. 2024Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing18 Apr
  30. 2024Stream of Search (SoS): Learning to Search in Language1 Apr
  31. 2024V-STaR: Training Verifiers for Self-Taught Reasoners9 Feb
  32. 2024ReFT: Reasoning with Reinforced Fine-Tuning17 Jan
  33. 2023Alphazero-like Tree-Search can Guide Large Language Model Decoding and Training29 Sep
  34. 2023CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing19 May
  35. 2023Self-Evaluation Guided Beam Search for Reasoning1 May
  36. 2023Self-Refine: Iterative Refinement with Self-Feedback30 Mar

Other references · 173

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2022Training language models to follow instructions with human feedbackcited by 15,971
  3. 2017Proximal Policy Optimization Algorithmscited by 15,215
  4. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  5. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  6. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  7. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  8. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  9. 2020Scaling Laws for Neural Language Modelscited by 6,586
  10. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  11. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  12. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,371
38 more
  1. 2023Let's Verify Step by Stepcited by 3,789
  2. 2023SWE-bench: Can Language Models Resolve Real-World GitHub Issues?cited by 3,373
  3. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 3,050
  4. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,879
  5. 2025DAPO: An Open-Source LLM Reinforcement Learning System at Scalecited by 2,810
  6. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,592
  7. 2023G-Eval: NLG Evaluation using GPT-4 with Better Human Alignmentcited by 2,276
  8. 2023MMBench: Is Your Multi-modal Model an All-around Player?cited by 2,141
  9. 2023MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGIcited by 2,080
  10. 2023WebArena: A Realistic Web Environment for Building Autonomous Agentscited by 2,006
  11. 2024LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Codecited by 2,004
  12. 2024MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmarkcited by 1,848
  13. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  14. 2023MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contextscited by 1,614
  15. 2022Competition-Level Code Generation with AlphaCodecited by 1,462
  16. 2023LongBench: A Bilingual, Multitask Benchmark for Long Context Understandingcited by 1,417
  17. 2024τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domainscited by 1,402
  18. 2022Solving Quantitative Reasoning Problems with Language Modelscited by 1,392
  19. 2020What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Examscited by 1,356
  20. 2022WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agentscited by 1,251
  21. 2023MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilitiescited by 1,239
  22. 2025Kimi k1.5: Scaling Reinforcement Learning with LLMscited by 1,210
  23. 2024OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problemscited by 1,136
  24. 2022Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Taskscited by 1,076
  25. 2024Tulu 3: Pushing Frontiers in Open Language Model Post-Trainingcited by 1,053
  26. 2023Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debatecited by 1,011
  27. 2024Large Language Monkeys: Scaling Inference Compute with Repeated Samplingcited by 991
  28. 2023Teaching Large Language Models to Self-Debugcited by 988
  29. 2024SimPO: Simple Preference Optimization with a Reference-Free Rewardcited by 963
  30. 2023Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotationscited by 928
  31. 2022Solving math word problems with process- and outcome-based feedbackcited by 901
  32. 2024Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluatorscited by 897
  33. 2024Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMscited by 838
  34. 2024Training Large Language Models to Reason in a Continuous Latent Spacecited by 797
  35. 2023AGIEval: A Human-Centric Benchmark for Evaluating Foundation Modelscited by 716
  36. 2023C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Modelscited by 708
  37. 2018Object Hallucination in Image Captioningcited by 669
  38. 2023LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusioncited by 564

50 most cited of 173 All 173 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 106; 2026: 117.

223 papers.

Sort:

By area:

  1. 2025A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligencecited by 170
  2. 2025General-Reasoner: Advancing LLM Reasoning Across All Domainscited by 135
  3. 2025A Survey of Context Engineering for Large Language Modelscited by 126
  4. 2025Reasoning Beyond Language: A Comprehensive Survey on Latent Chain-of-Thought Reasoningcited by 78
  5. 2025A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challengescited by 62
  6. 2025Enigmata: Scaling Logical Reasoning in Large Language Models with Synthetic Verifiable Puzzlescited by 56
  7. 2025AdaCtrl: Towards Adaptive and Controllable Reasoning via Difficulty-Aware Budgetingcited by 50
  8. 2025Implicit Reasoning in Large Language Models: A Comprehensive Surveycited by 43
  9. 2025Reinforcement Pre-Trainingcited by 40
  10. 2025Long-Short Chain-of-Thought Mixture Supervised Fine-Tuning Eliciting Efficient Reasoning in Large Language Modelscited by 39
  11. 2025A Survey of Process Reward Models: From Outcome Signals to Process Supervisions for Large Language Modelscited by 38
  12. 2025VCRL: Variance-based Curriculum Reinforcement Learning for Large Language Modelscited by 36
38 more
  1. 2025Recursive Self-Aggregation Unlocks Deep Thinking in Large Language Modelscited by 35
  2. 2025Visual Document Understanding and Reasoning: A Multi-Agent Collaboration Framework with Agent-Wise Adaptive Test-Time Scalingcited by 30
  3. 2025SpecDiff-2: Scaling Diffusion Drafter Alignment For Faster Speculative Decodingcited by 26
  4. 2025OpenCodeReasoning-II: A Simple Test Time Scaling Approach via Self-Critiquecited by 25
  5. 2025Agentar-Scale-SQL: Advancing Text-to-SQL through Orchestrated Test-Time Scalingcited by 24
  6. 2025Group Think: Multiple Concurrent Reasoning Agents Collaborating at Token Level Granularitycited by 22
  7. 2025AI Scientists Fail Without Strong Implementation Capabilitycited by 21
  8. 2026Structured Scaling of AI Discovery Across Diverse Scientific Domainscited by 21
  9. 2026Stabilizing Recurrent Dynamics for Test-Time Scalable Latent Reasoning in Looped Language Modelscited by 21
  10. 2025Not All Tokens Are What You Need In Thinkingcited by 20
  11. 2025Can Slow-thinking LLMs Reason Over Time? Empirical Studies in Time Series Forecastingcited by 20
  12. 2025Explicit v.s. Implicit Memory: Exploring Multi-hop Complex Reasoning Over Personalized Informationcited by 17
  13. 2025Learning from Peers in Reasoning Modelscited by 16
  14. 2025Staying in the Sweet Spot: Responsive Reasoning Evolution via Capability-Adaptive Hint Scaffoldingcited by 16
  15. 2026SWE-TRACE: Optimizing Long-Horizon SWE Agents Through Rubric Process Reward Models and Heuristic Test-Time Scalingcited by 16
  16. 2025Generative AI Act II: Test Time Scaling Drives Cognition Engineeringcited by 15
  17. 2025CSC-SQL: Corrective Self-Consistency in Text-to-SQL via Reinforcement Learningcited by 15
  18. 2026Scaling Test-Time Compute for Agentic Codingcited by 15
  19. 2025Query-Level Uncertainty in Large Language Modelscited by 14
  20. 2025Aware First, Think Less: Dynamic Boundary Self-Awareness Drives Extreme Reasoning Efficiency in Large Language Modelscited by 13
  21. 2025Slim-SC: Thought Pruning for Efficient Scaling with Self-Consistencycited by 13
  22. 2026Falcon-H1R: Pushing the Reasoning Frontiers with a Hybrid Model for Efficient Test-Time Scalingcited by 13
  23. 2026Inference-Time Budget Control for LLM Search Agentscited by 13
  24. 2025ROC-n-reroll: How verifier imperfection affects test-time scalingcited by 12
  25. 2025Efficient Test-Time Scaling for Small Vision-Language Modelscited by 12
  26. 2025The Art of Scaling Test-Time Compute for Large Language Modelscited by 12
  27. 2026SWE-Replay: Efficient Test-Time Scaling for Software Engineering Agentscited by 12
  28. 2025Slow Thinking for Sequential Recommendationcited by 11
  29. 2025UORA: Uniform Orthogonal Reinitialization Adaptation in Parameter-Efficient Fine-Tuning of Large Modelscited by 11
  30. 2025Scaling over Scaling: Exploring Test-Time Scaling Plateau in Large Reasoning Modelscited by 11
  31. 2025Guided Speculative Inference for Efficient Test-Time Alignment of LLMscited by 11
  32. 2025Test-Time Scaling in Reasoning Models Is Not Effective for Knowledge-Intensive Tasks Yetcited by 11
  33. 2026Spark: Strategic Policy-Aware Exploration via Dynamic Branching for Long-Horizon Agentic Learningcited by 11
  34. 2025A Survey of Scaling in Large Language Model Reasoningcited by 10
  35. 2025SLM-SQL: An Exploration of Small Language Models for Text-to-SQLcited by 10
  36. 2025Scaling Test-Time Compute to Achieve IOI Gold Medal with Open-Weight Modelscited by 10
  37. 2025SolverLLM: Leveraging Test-Time Scaling for Optimization Problem via LLM-Guided Searchcited by 10
  38. 2025RAPO++: Cross-Stage Prompt Optimization for Text-to-Video Generation via Data Alignment and Test-Time Scalingcited by 10

50 most cited of 223 All 223 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Are We Scaling the Right Thing? A System Perspective on Test-Time Scaling
  2. 2025Test-time Scaling of LLMs: A Survey from A Subproblem Structure Perspective
  3. 2025Inference-Time Scaling for Complex Tasks: Where We Stand and What Lies Ahead
  4. 2025Scaling Test-time Compute for LLM Agents
  5. 2025AgentTTS: Large Language Model Agent for Test-time Compute-optimal Scaling Strategy in Complex Tasks
  6. 2026Test-Time Scaling in Reasoning LLMs: Inference Regimes, Evaluation, and Reproducibility
  7. 2025Z1: Efficient Test-time Scaling with Code
  8. 2025SETS: Leveraging Self-Verification and Self-Correction for Improved Test-Time Scaling