mlsanityData to 7 Oct 2026

SETS: Leveraging Self-Verification and Self-Correction for Improved Test-Time Scaling

arXiv 2501.19306 ↗First posted 31 Jan 2025cs.AI cs.CLcited by 54

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

Abstract (arXiv)

Recent advancements in Large Language Models (LLMs) have created new opportunities to enhance performance on complex reasoning tasks by leveraging test-time computation. However, existing scaling methods have key limitations: parallel methods like repeated sampling are often inefficient and quickly saturate, while sequential methods like SELF-REFINE struggle to improve after a few rounds. Although combining these approaches shows promise, current methods require fine-tuned reward and revision models. This paper proposes Self-Enhanced Test-Time Scaling (SETS), a simple yet effective approach that overcomes these limitations by strategically combining parallel and sequential techniques and fully leveraging LLMs' self-improvement abilities. SETS exploits the inherent self-verification and self-correction capabilities of LLMs, unifying sampling, verification, and correction within a single framework. This facilitates efficient and scalable test-time computation for enhanced performance on complex tasks without any model training. Our comprehensive experimental results on challenging benchmarks spanning planning, reasoning, math, and coding demonstrate that SETS achieves significant performance improvements and more advantageous test-time scaling behavior than the alternatives.

Key facts. Cited by 54 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 33 of its 51 references that are in the map. First posted on arXiv 31 Jan 2025.

Builds on

33 of 51 references.

Closest ancestors · 10

Same direction, newest first

  1. 2025Evolving Deeper LLM Thinking17 Jan
  2. 2024Scaling LLM Inference with Optimized Sample Compute Allocation29 Oct
  3. 2024LLM Self-Correction with DeCRIM: Decompose, Critique, and Refine for Enhanced Following of Instructions with Multiple Constraints9 Oct
  4. 2024Improving LLM Reasoning through Scaling Inference Computation with Collaborative Verification5 Oct
  5. 2024Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters6 Aug
  6. 2023Universal Self-Consistency for Large Language Model Generation29 Nov
  7. 2023Large Language Models Cannot Self-Correct Reasoning Yet3 Oct
  8. 2023CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing19 May
  9. 2023Self-Refine: Iterative Refinement with Self-Feedback30 Mar
  10. 2022Language Models (Mostly) Know What They Know11 Jul

Other references · 23

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  4. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  5. 2020Scaling Laws for Neural Language Modelscited by 6,411
  6. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  7. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,203
  8. 2017On Calibration of Modern Neural Networkscited by 4,860
  9. 2017Deep reinforcement learning from human preferencescited by 3,846
  10. 2023Let's Verify Step by Stepcited by 3,598
  11. 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,175
  12. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
11 more
  1. 2024LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Codecited by 1,906
  2. 2024Large Language Monkeys: Scaling Inference Compute with Repeated Samplingcited by 946
  3. 2017Selective Classification for Deep Neural Networkscited by 799
  4. 2022Large Language Models are Better Reasoners with Self-Verificationcited by 304
  5. 2022Out-of-Distribution Detection and Selective Generation for Conditional Language Modelscited by 193
  6. 2024Recursive Introspection: Teaching Language Model Agents How to Self-Improvecited by 162
  7. 2024From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Modelscited by 136
  8. 2024NATURAL PLAN: Benchmarking LLMs on Natural Language Planningcited by 125
  9. 2023Self-Evaluation Improves Selective Generation in Large Language Modelscited by 74
  10. 2024TICKing All the Boxes: Generated Checklists Improve LLM Evaluation and Generationcited by 62
  11. 2023Adaptation with Self-Evaluation to Improve Selective Prediction in LLMscited by 49

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 40; 2026: 14.

54 papers.

Sort:

By area:

  1. 2025Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Modelscited by 381
  2. 2025Efficient Test-Time Scaling via Self-Calibrationcited by 74
  3. 2025Hume: Introducing System-2 Thinking in Visual-Language-Action Modelcited by 56
  4. 2025Reflect-DiT: Inference-Time Scaling for Text-to-Image Diffusion Transformers via In-Context Reflectioncited by 42
  5. 2025Budget-Aware Tool Use Enables Effective Agent Scalingcited by 42
  6. 2025When To Solve, When To Verify: Compute-Optimal Problem Solving and Generative Verification for LLM Reasoningcited by 41
  7. 2025S2R: Teaching LLMs to Self-verify and Self-correct via Reinforcement Learningcited by 37
  8. 2025UniGen: Enhanced Training & Test-Time Strategies for Unified Multimodal Understanding and Generationcited by 32
  9. 2025Thinking Machines: A Survey of LLM based Reasoning Strategiescited by 25
  10. 2025Stronger-MAS: Multi-Agent Reinforcement Learning for Collaborative LLMscited by 25
  11. 2025Shrinking the Generation-Verification Gap with Weak Verifierscited by 21
  12. 2025On the Effect of Sampling Diversity in Scaling LLM Inferencecited by 18
38 more
  1. 2025Beyond 'Aha!': Toward Systematic Meta-Abilities Alignment in Large Reasoning Modelscited by 17
  2. 2025Reasoning Beyond Limits: Advances and Open Problems for LLMscited by 16
  3. 2025Generative AI Act II: Test Time Scaling Drives Cognition Engineeringcited by 14
  4. 2025Putting the Value Back in RL: Better Test-Time Scaling by Unifying LLM Reasoners With Verifierscited by 14
  5. 2025TUMIX: Multi-Agent Test-Time Scaling with Tool-Use Mixturecited by 13
  6. 2026Parallel-Probe: Towards Efficient Parallel Thinking via 2D Probingcited by 13
  7. 2026Inference-Time Budget Control for LLM Search Agentscited by 13
  8. 2025Sample Complexity and Representation Ability of Test-time Scaling Paradigmscited by 12
  9. 2025Scaling over Scaling: Exploring Test-Time Scaling Plateau in Large Reasoning Modelscited by 11
  10. 2025When Does Verification Pay Off? A Closer Look at LLMs as Solution Verifierscited by 11
  11. 2025Scaling LLM Test-Time Compute with Mobile NPU on Smartphonescited by 9
  12. 2025Solve-Detect-Verify: Inference-Time Scaling with Flexible Generative Verifiercited by 7
  13. 2025DynScaling: Efficient Verifier-free Inference Scaling via Dynamic and Integrated Samplingcited by 7
  14. 2026From Scale to Speed: Adaptive Test-Time Scaling for Image Editingcited by 7
  15. 2025AutoChemSchematic AI: Agentic Physics-Aware Automation for Chemical Manufacturing Scale-Upcited by 6
  16. 2025EvoMem: Improving Multi-Agent Planning with Dual-Evolving Memorycited by 6
  17. 2025SSR: Socratic Self-Refine for Large Language Model Reasoningcited by 6
  18. 2025Scaling Test-Time Inference with Policy-Optimized, Dynamic Retrieval-Augmented Generation via KV Caching and Decodingcited by 4
  19. 2025A Short Survey on Small Reasoning Models: Training, Inference, Applications and Research Directionscited by 4
  20. 2025Unifying Dynamic Tool Creation and Cross-Task Experience Sharing through Cognitive Memory Architecturecited by 4
  21. 2025A Study on Leveraging Search and Self-Feedback for Agent Reasoningcited by 3
  22. 2025Self-Correcting Code Generation Using Small Language Modelscited by 3
  23. 2025Reasoning over Boundaries: Enhancing Specification Alignment via Test-time Deliberationcited by 3
  24. 2025No Labels, No Problem: Training Visual Reasoners with Multimodal Verifierscited by 3
  25. 2026Understanding Performance Gap Between Parallel and Sequential Sampling in Large Reasoning Modelscited by 3
  26. 2026Beyond Verifiable Rewards: Rubric-Based GRM for Reinforced Fine-Tuning SWE Agentscited by 3
  27. 2026How LLMs Detect and Correct Their Own Errors: The Role of Internal Confidence Signalscited by 3
  28. 2025Boosting Accuracy and Efficiency of Budget Forcing in LLMs via Reinforcement Learning for Mathematical Reasoningcited by 2
  29. 2025TextualVerifier: Verify TextGrad Step-by-Stepcited by 2
  30. 2026SNEAK: Evaluating Strategic Communication and Information Leakage in Large Language Modelscited by 2
  31. 2025Sample-Efficient Optimization over Generative Priors via Coarse Learnabilitycited by 1
  32. 2025MatryoshkaThinking: Recursive Test-Time Scaling Enables Efficient Reasoningcited by 1
  33. 2025SELF-REDRAFT: Eliciting Intrinsic Exploration-Exploitation Balance in Test-Time Scaling for Code Generationcited by 1
  34. 2025FutureWeaver: Planning Test-Time Compute for Multi-Agent Systems with Modularized Collaborationcited by 1
  35. 2026The Future of Facts: Tracing the Factual Generation-Verification Gapcited by 1
  36. 2025Advancing AI Research Assistants with Expert-Involved Learningcited by 0
  37. 2026MarkovScale: Towards Optimal Sequential Scaling at Inference Timecited by 0
  38. 2026RefineRL: Advancing Competitive Programming with Self-Refinement Reinforcement Learningcited by 0

50 most cited of 54 All 54 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025The Art of Scaling Test-Time Compute for Large Language Models
  2. 2025Iterative Deepening Sampling as Efficient Test-Time Scaling
  3. 2025A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well?
  4. 2025A Theoretical Study on Bridging Internal Probability and Self-Consistency for LLM Reasoning
  5. 2025Scaling Test-time Compute for LLM Agents
  6. 2026Test-Time Scaling in Reasoning LLMs: Inference Regimes, Evaluation, and Reproducibility
  7. 2026ThinkBooster: A Unified Framework for Seamless Test-Time Scaling of LLM Reasoning
  8. 2026How Much Can Language Models Gain from Test-Time Computation?