mlsanityData to 14 Oct 2026

Revisiting Test-Time Scaling: A Survey and a Diversity-Aware Method for Efficient Reasoning

arXiv 2506.04611 ↗First posted 5 Jun 2025cs.CLcited by 9

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

Abstract (arXiv)

Test-Time Scaling (TTS) improves the reasoning performance of Large Language Models (LLMs) by allocating additional compute during inference. We conduct a structured survey of TTS methods and categorize them into sampling-based, search-based, and trajectory optimization strategies. We observe that reasoning-optimized models often produce less diverse outputs, which limits TTS effectiveness. To address this, we propose ADAPT (A Diversity Aware Prefix fine-Tuning), a lightweight method that applies prefix tuning with a diversity-focused data strategy. Experiments on mathematical reasoning tasks show that ADAPT reaches 80% accuracy using eight times less compute than strong baselines. Our findings highlight the essential role of generative diversity in maximizing TTS effectiveness.

Key facts. Cited by 9 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 78 of its 104 references that are in the map. First posted on arXiv 5 Jun 2025.

Builds on

78 of 104 references.

Closest ancestors · 19

Same direction, newest first

  1. 2025A Survey of Slow Thinking-based Reasoning LLMs using Reinforced Learning and Inference-time Scaling Law5 May
  2. 2025Sleep-time Compute: Beyond Inference Scaling at Test-time17 Apr
  3. 2025Efficient Reasoning Models: A Survey15 Apr
  4. 2025Weight Ensembling Improves Reasoning in Language Models14 Apr
  5. 2025Harnessing the Reasoning Economy: A Survey of Efficient Reasoning for Large Language Models31 Mar
  6. 2025A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well?31 Mar
  7. 2025Think Twice: Enhancing LLM Reasoning by Scaling Multi-round Test-time Thinking25 Mar
  8. 2025Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models20 Mar
  9. 2025Efficient Test-Time Scaling via Self-Calibration25 Feb
  10. 2025Towards Thinking-Optimal Scaling of Test-Time Compute for LLM Reasoning25 Feb
  11. 2025Reasoning with Latent Thoughts: On the Power of Looped Transformers24 Feb
  12. 2025Scaling Test-Time Compute Without Verification or RL is Suboptimal17 Feb
7 more
  1. 2025Atom of Thoughts for Markov LLM Test-Time Scaling17 Feb
  2. 2025Rethinking Fine-Tuning when Scaling Test-Time Compute: Limiting Confidence Improves Mathematical Reasoning11 Feb
  3. 2025Latent Thought Models with Variational Bayes Inference-Time Computation3 Feb
  4. 2024Inference-Aware Fine-Tuning for Best-of-N Sampling in Large Language Models18 Dec
  5. 2024Forest-of-Thought: Scaling Test-Time Compute for Enhancing LLM Reasoning12 Dec
  6. 2024Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters6 Aug
  7. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Models17 May

Other references · 59

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  3. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  4. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  5. 2020Scaling Laws for Neural Language Modelscited by 6,586
  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. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,326
  9. 2018Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challengecited by 4,886
  10. 2023Let's Verify Step by Stepcited by 3,789
  11. 2021Program Synthesis with Large Language Modelscited by 3,637
  12. 2022Training Compute-Optimal Large Language Modelscited by 3,019
38 more
  1. 2024LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Codecited by 2,004
  2. 2024MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmarkcited by 1,848
  3. 2024OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problemscited by 1,136
  4. 2025Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?cited by 982
  5. 2025Cosmos World Foundation Model Platform for Physical AIcited by 864
  6. 2024Training Large Language Models to Reason in a Continuous Latent Spacecited by 797
  7. 2023Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizescited by 737
  8. 2022Automatic Chain of Thought Prompting in Large Language Modelscited by 688
  9. 2022PAL: Program-aided Language Modelscited by 652
  10. 2024GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Modelscited by 550
  11. 2024Mixture-of-Agents Enhances Large Language Model Capabilitiescited by 438
  12. 2024Robotic Control via Embodied Chain-of-Thought Reasoningcited by 346
  13. 2025Chain of Draft: Thinking Faster by Writing Lesscited by 297
  14. 2023Towards Revealing the Mystery behind Chain of Thought: A Theoretical Perspectivecited by 294
  15. 2025Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Modelscited by 293
  16. 2024Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Modelscited by 284
  17. 2022Transformers Learn Shortcuts to Automatacited by 268
  18. 2024Chain of Thought Empowers Transformers to Solve Inherently Serial Problemscited by 260
  19. 2024Monte Carlo Tree Search Boosts Reasoning via Iterative Preference Learningcited by 241
  20. 2025CODI: Compressing Chain-of-Thought into Continuous Space via Self-Distillationcited by 225
  21. 2022Distilling Reasoning Capabilities into Smaller Language Modelscited by 158
  22. 2024From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Modelscited by 137
  23. 2025LLM Post-Training: A Deep Dive into Reasoning Large Language Modelscited by 135
  24. 2025Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuningcited by 123
  25. 2025One-Minute Video Generation with Test-Time Trainingcited by 101
  26. 2025Is Best-of-N the Best of Them? Coverage, Scaling, and Optimality in Inference-Time Alignmentcited by 97
  27. 2025A Sober Look at Progress in Language Model Reasoning: Pitfalls and Paths to Reproducibilitycited by 93
  28. 2025A Survey on Post-training of Large Language Modelscited by 54
  29. 2024The Limits of Inference Scaling Through Resamplingcited by 53
  30. 2021AR-LSAT: Investigating Analytical Reasoning of Textcited by 51
  31. 2023The Expressive Power of Transformers with Chain of Thoughtcited by 50
  32. 2025Stop Summation: Min-Form Credit Assignment Is All Process Reward Model Needs for Reasoningcited by 50
  33. 2025m1: Unleash the Potential of Test-Time Scaling for Medical Reasoning with Large Language Modelscited by 46
  34. 2025Synthetic Data Generation & Multi-Step RL for Reasoning & Tool Usecited by 45
  35. 2025Unveiling the Key Factors for Distilling Chain-of-Thought Reasoningcited by 40
  36. 2025Z1: Efficient Test-time Scaling with Codecited by 35
  37. 2025Transformers Learn to Implement Multi-step Gradient Descent with Chain of Thoughtcited by 32
  38. 2025Two Heads are Better Than One: Test-time Scaling of Multi-agent Collaborative Reasoningcited by 29

50 most cited of 59 All 59 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 4; 2026: 5.

9 papers.

  1. 2025Reasoning Path Divergence: A New Metric and Curation Strategy to Unlock LLM Diverse Thinkingcited by 10
  2. 2025LatentEvolve: Self-Evolving Test-Time Scaling in Latent Spacecited by 9
  3. 2025Trust but Verify! A Survey on Verification Design for Test-time Scalingcited by 8
  4. 2026LaDi-RL: Latent Diffusion Reasoning Prevents Entropy Collapse in Reinforcement Learningcited by 7
  5. 2025Test-time Diverse Reasoning by Riemannian Activation Steeringcited by 4
  6. 2026A Survey on Self-Improving Test-Time Intelligence: Feedback-Driven Adapting, Learning, and Scaling at Inferencecited by 3
  7. 2026From Exposure to Internalization: Dual-Stream Calibration for In-context Clinical Reasoningcited by 0
  8. 2026It's the Decoding Format, Not the Perturbation: Auditing Consistency-Based Selection for Vision-Language Test-Time Scalingcited by 0
  9. 2026When does a scaling result justify a different allocation? A critical review of resource-allocation evidence for AI systemscited 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. 2025Are We Scaling the Right Thing? A System Perspective on Test-Time Scaling
  3. 2026ThinkBooster: A Unified Framework for Seamless Test-Time Scaling of LLM Reasoning
  4. 2025Scaling over Scaling: Exploring Test-Time Scaling Plateau in Large Reasoning Models
  5. 2025Mitigating Strategy-Selection Bias in Reasoning for More Effective Test-Time Scaling
  6. 2025Prompting Test-Time Scaling Is A Strong LLM Reasoning Data Augmentation
  7. 2025Reasoning on a Budget: A Survey of Adaptive and Controllable Test-Time Compute in LLMs
  8. 2025ARISE: An Adaptive Resolution-Aware Metric for Test-Time Scaling Evaluation in Large Reasoning Models