mlsanityData to 7 Oct 2026

A Survey of Test-Time Compute: From Intuitive Inference to Deliberate Reasoning

arXiv 2501.02497 ↗First posted 5 Jan 2025cs.AI cs.CL cs.LGcited by 40

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

Abstract (arXiv)

The remarkable performance of the o1 model in complex reasoning demonstrates that test-time compute scaling can further unlock the model's potential, enabling powerful System-2 thinking. However, there is still a lack of comprehensive surveys for test-time compute scaling. We trace the concept of test-time compute back to System-1 models. In System-1 models, test-time compute addresses distribution shifts and improves robustness and generalization through parameter updating, input modification, representation editing, and output calibration. In System-2 models, it enhances the model's reasoning ability to solve complex problems through repeated sampling, self-correction, and tree search. We organize this survey according to the trend of System-1 to System-2 thinking, highlighting the key role of test-time compute in the transition from System-1 models to weak System-2 models, and then to strong System-2 models. We also point out advanced topics and future directions.

Key facts. Cited by 40 papers in the map (data through 7 Oct 2026). Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning. Builds on 238 of its 387 references that are in the map. First posted on arXiv 5 Jan 2025.

Builds on

238 of 387 references.

Closest ancestors · 29

Same direction, newest first

  1. 2024Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs30 Dec
  2. 2024Understanding the Dark Side of LLMs' Intrinsic Self-Correction19 Dec
  3. 2024Think&Cite: Improving Attributed Text Generation with Self-Guided Tree Search and Progress Reward Modeling19 Dec
  4. 2024Compressed Chain of Thought: Efficient Reasoning Through Dense Representations17 Dec
  5. 2024C3oT: Generating Shorter Chain-of-Thought without Compromising Effectiveness16 Dec
  6. 2024Forest-of-Thought: Scaling Test-Time Compute for Enhancing LLM Reasoning12 Dec
  7. 2024Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision25 Nov
  8. 2024O1 Replication Journey -- Part 2: Surpassing O1-preview through Simple Distillation, Big Progress or Bitter Lesson?25 Nov
  9. 2024Marco-o1: Towards Open Reasoning Models for Open-Ended Solutions21 Nov
  10. 2024Scaling LLM Inference with Optimized Sample Compute Allocation29 Oct
  11. 2024TreeBoN: Enhancing Inference-Time Alignment with Speculative Tree-Search and Best-of-N Sampling18 Oct
  12. 2024Embedding Self-Correction as an Inherent Ability in Large Language Models for Enhanced Mathematical Reasoning14 Oct
17 more
  1. 2024O1 Replication Journey: A Strategic Progress Report -- Part 18 Oct
  2. 2024Learning How Hard to Think: Input-Adaptive Allocation of LM Computation7 Oct
  3. 2024Interpretable Contrastive Monte Carlo Tree Search Reasoning2 Oct
  4. 2024Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters6 Aug
  5. 2024Reasoning in Token Economies: Budget-Aware Evaluation of LLM Reasoning Strategies10 Jun
  6. 2024CriticBench: Benchmarking LLMs for Critique-Correct Reasoning22 Feb
  7. 2024V-STaR: Training Verifiers for Self-Taught Reasoners9 Feb
  8. 2023Just Ask One More Time! Self-Agreement Improves Reasoning of Language Models in (Almost) All Scenarios14 Nov
  9. 2023Think before you speak: Training Language Models With Pause Tokens3 Oct
  10. 2023Large Language Models Cannot Self-Correct Reasoning Yet3 Oct
  11. 2023Alphazero-like Tree-Search can Guide Large Language Model Decoding and Training29 Sep
  12. 2023Shepherd: A Critic for Language Model Generation8 Aug
  13. 2023Let's Sample Step by Step: Adaptive-Consistency for Efficient Reasoning and Coding with LLMs19 May
  14. 2023CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing19 May
  15. 2023Large Language Model Guided Tree-of-Thought15 May
  16. 2023REFINER: Reasoning Feedback on Intermediate Representations4 Apr
  17. 2023Self-Refine: Iterative Refinement with Self-Feedback30 Mar

Other references · 209

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2022Training language models to follow instructions with human feedbackcited by 15,712
  4. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  5. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  6. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  7. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  8. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  9. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  10. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,203
  11. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  12. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,195
38 more
  1. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  2. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,769
  3. 2021Program Synthesis with Large Language Modelscited by 3,509
  4. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 2,950
  5. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  6. 2020Learning to summarize from human feedbackcited by 2,562
  7. 2023G-Eval: NLG Evaluation using GPT-4 with Better Human Alignmentcited by 2,205
  8. 2023Code Llama: Open Foundation Models for Codecited by 2,105
  9. 2020Shortcut Learning in Deep Neural Networkscited by 1,928
  10. 2020The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalizationcited by 1,842
  11. 2024MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmarkcited by 1,758
  12. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,739
  13. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,722
  14. 2022Fast Inference from Transformers via Speculative Decodingcited by 1,615
  15. 2022Competition-Level Code Generation with AlphaCodecited by 1,427
  16. 2022Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference timecited by 1,366
  17. 2023Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generationcited by 1,332
  18. 2023Inference-Time Intervention: Eliciting Truthful Answers from a Language Modelcited by 1,259
  19. 2021What Makes Good In-Context Examples for GPT-3?cited by 1,184
  20. 2019A Comprehensive Survey on Transfer Learningcited by 1,154
  21. 2021Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivitycited by 1,122
  22. 2024OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problemscited by 1,099
  23. 2022Scaling Laws for Reward Model Overoptimizationcited by 1,056
  24. 2023Large Language Models are not Fair Evaluatorscited by 1,050
  25. 2020COMET: A Neural Framework for MT Evaluationcited by 1,024
  26. 2019Learning Robust Global Representations by Penalizing Local Predictive Powercited by 1,010
  27. 2023Steering Llama 2 via Contrastive Activation Additioncited by 1,009
  28. 2024Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Predictioncited by 1,005
  29. 2023Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debatecited by 995
  30. 2023Teaching Large Language Models to Self-Debugcited by 963
  31. 2024Refusal in Language Models Is Mediated by a Single Directioncited by 960
  32. 2024Large Language Monkeys: Scaling Inference Compute with Repeated Samplingcited by 946
  33. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 911
  34. 2023Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotationscited by 895
  35. 2022Solving math word problems with process- and outcome-based feedbackcited by 871
  36. 2023Reasoning with Language Model is Planning with World Modelcited by 846
  37. 2023Steering Language Models With Activation Engineeringcited by 824
  38. 2019Plug and Play Language Models: A Simple Approach to Controlled Text Generationcited by 793

50 most cited of 209 All 209 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 25; 2026: 15.

40 papers.

Sort:

By area:

  1. 2025Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Modelscited by 381
  2. 2025Llasa: Scaling Train-Time and Inference-Time Compute for Llama-based Speech Synthesiscited by 69
  3. 2025Evaluating Judges as Evaluators: The JETTS Benchmark of LLM-as-Judges as Test-Time Scaling Evaluatorscited by 42
  4. 2025MCTS-Judge: Test-Time Scaling in LLM-as-a-Judge for Code Correctness Evaluationcited by 32
  5. 2025Leaky Thoughts: Large Reasoning Models Are Not Private Thinkerscited by 25
  6. 2025Group Think: Multiple Concurrent Reasoning Agents Collaborating at Token Level Granularitycited by 22
  7. 2025OmniThink: Expanding Knowledge Boundaries in Machine Writing through Thinkingcited by 18
  8. 2025R4ec: A Reasoning, Reflection, and Refinement Framework for Recommendation Systemscited by 16
  9. 2025Generative AI Act II: Test Time Scaling Drives Cognition Engineeringcited by 14
  10. 2025MetaScale: Test-Time Scaling with Evolving Meta-Thoughtscited by 13
  11. 2025Test-time Prompt Interventioncited by 12
  12. 2025Rethinking the Role of Prompting Strategies in LLM Test-Time Scaling: A Perspective of Probability Theorycited by 10
28 more
  1. 2025Inference Computation Scaling for Feature Augmentation in Recommendation Systemscited by 5
  2. 2025Reasoning Transfer for an Extremely Low-Resource and Endangered Language: Bridging Languages Through Sample-Efficient Language Understandingcited by 5
  3. 2025Multilingual Test-Time Scaling via Initial Thought Transfercited by 5
  4. 2025Socratic-PRMBench: Benchmarking Process Reward Models with Systematic Reasoning Patternscited by 5
  5. 2026When Is Thinking Enough? Early Exit via Sufficiency Assessment for Efficient Reasoningcited by 5
  6. 2025Scaling Test-Time Inference with Policy-Optimized, Dynamic Retrieval-Augmented Generation via KV Caching and Decodingcited by 4
  7. 2025Can Past Experience Accelerate LLM Reasoning?cited by 3
  8. 2025Less Data Less Tokens: Multilingual Unification Learning for Efficient Test-Time Reasoning in LLMscited by 3
  9. 2025Explicit Reasoning Makes Better Judges: A Systematic Study on Accuracy, Efficiency, and Robustnesscited by 3
  10. 2026Attention-MoA: Enhancing Mixture-of-Agents via Inter-Agent Semantic Attention and Deep Residual Synthesiscited by 3
  11. 2025Mitigating Strategy-Selection Bias in Reasoning for More Effective Test-Time Scalingcited by 2
  12. 2026Guided by the Plan: Enhancing Faithful Autoregressive Text-to-Audio Generation with Guided Decodingcited by 2
  13. 2026Linking Perception, Confidence and Accuracy in MLLMscited by 2
  14. 2025SoT: Structured-of-Thought Prompting Guides Multilingual Reasoning in Large Language Modelscited by 1
  15. 2025FEval-TTC: Fair Evaluation Protocol for Test-Time Computecited by 1
  16. 2026When to Trust Tools? Adaptive Tool Trust Calibration For Tool-Integrated Math Reasoningcited by 1
  17. 2026Verifier-Guided Code Translation via Meta-Step Decodingcited by 1
  18. 2026AutoCRAT: Within-trajectory Joint Control of Stochasticity and Compute for LLM Reasoningcited by 1
  19. 2025RECIPE-TKG: From Sparse History to Structured Reasoning for LLM-based Temporal Knowledge Graph Completioncited by 0
  20. 2025Stepwise Reasoning Checkpoint Analysis: A Test Time Scaling Method to Enhance LLMs' Reasoningcited by 0
  21. 2026From Sycophancy to Sensemaking: Premise Governance for Human-AI Decision Makingcited by 0
  22. 2026MAPLE: Elevating Medical Reasoning from Statistical Consensus to Process-Led Alignmentcited by 0
  23. 2026When to Vote, When to Rewrite: Disagreement-Guided Strategy Routing for Test-Time Scalingcited by 0
  24. 2026Test-Time Scaling in Multimodal Foundation Models: A Comprehensive Survey of Generation and Reasoningcited by 0
  25. 2026Shattering the Autoregressive Curse: Dynamic Epistemic Entropy Orchestrated Erasable Reinforcement Learning for LLMscited by 0
  26. 2026OpenClaw and Ollama in Agentic AI: Toward Fully Autonomous and Scalable AI Agent Systemscited by 0
  27. 2026MILO: Efficient Many-shot In-Context Learning with Block-wise Low-rank Compressioncited by 0
  28. 2026SemOPT: Fixing Semantic Errors in LLM-based Optimization Modeling via Reward-Guided Searchcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025The Art of Scaling Test-Time Compute for Large Language Models
  2. 2025Scaling over Scaling: Exploring Test-Time Scaling Plateau in Large Reasoning Models
  3. 2025Are We Scaling the Right Thing? A System Perspective on Test-Time Scaling
  4. 2026What If We Allocate Test-Time Compute Adaptively?
  5. 2025ARISE: An Adaptive Resolution-Aware Metric for Test-Time Scaling Evaluation in Large Reasoning Models
  6. 2025Test-Time Scaling in Reasoning Models Is Not Effective for Knowledge-Intensive Tasks Yet
  7. 2026Test-Time Scaling in Reasoning LLMs: Inference Regimes, Evaluation, and Reproducibility
  8. 2025Sample, Scrutinize and Scale: Effective Inference-Time Search by Scaling Verification