mlsanityData to 14 Oct 2026

Hint Tuning: Less Data Makes Better Reasoners

arXiv 2605.08665 ↗First posted 9 May 2026cs.CLcited by 1

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

Abstract (arXiv)

Large reasoning models achieve high accuracy through extended chain-of-thought but generate 5--8 more tokens than necessary, applying verbose reasoning uniformly regardless of problem difficulty. We propose Hint Tuning, a data-efficient approach that teaches models to calibrate reasoning depth. Our key insight: the corresponding instruct model serves as an ideal difficulty probe. By testing what the instruct model can solve with varying guidance, we automatically construct training data across three states: No-Hint (direct answer), Sparse-Hint (minimal prefix), and Full-Hint (complete reasoning). This converts the abstract challenge of difficulty labeling into a measurable consistency check between the instruct and reasoning models. With only 1K self-annotated samples, Hint Tuning achieves 24--66% token reduction (31.5% average) across mainstream reasoning models (Qwen3-Thinking, DeepSeek-R1-Distill) at multiple scales (4B--32B) while maintaining competitive accuracy on five benchmarks. Unlike methods requiring massive distillation datasets or expensive RL, we achieve superior efficiency through simple alignment with the instruct model's capabilities. Code and data are available at https://github.com/redai-infra/hint-tuning.

Key facts. Cited by 1 paper 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 35 of its 40 references that are in the map. First posted on arXiv 9 May 2026.

Builds on

35 of 40 references.

Closest ancestors · 16

Same direction, newest first

  1. 2026PACE: Prefix-Protected and Difficulty-Aware Compression for Efficient Reasoning12 Feb
  2. 2025VeriThinker: Learning to Verify Makes Reasoning Model Efficient23 May
  3. 2025AdaptThink: Reasoning Models Can Learn When to Think19 May
  4. 2025Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models20 Mar
  5. 2025L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning6 Mar
  6. 2025DAST: Difficulty-Adaptive Slow-Thinking for Large Reasoning Models6 Mar
  7. 2025Self-Training Elicits Concise Reasoning in Large Language Models27 Feb
  8. 2025TokenSkip: Controllable Chain-of-Thought Compression in LLMs17 Feb
  9. 2025CoT-Valve: Length-Compressible Chain-of-Thought Tuning13 Feb
  10. 2025Demystifying Long Chain-of-Thought Reasoning in LLMs5 Feb
  11. 2025s1: Simple test-time scaling31 Jan
  12. 2025O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning22 Jan
4 more
  1. 2024Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs30 Dec
  2. 2024Token-Budget-Aware LLM Reasoning24 Dec
  3. 2024C3oT: Generating Shorter Chain-of-Thought without Compromising Effectiveness16 Dec
  4. 2024Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters6 Aug

Other references · 19

  1. 2022Training language models to follow instructions with human feedbackcited by 15,971
  2. 2017Proximal Policy Optimization Algorithmscited by 15,215
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  4. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  5. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  6. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  7. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,371
  8. 2022Large Language Models are Zero-Shot Reasonerscited by 4,374
  9. 2023Let's Verify Step by Stepcited by 3,789
  10. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,879
  11. 2024LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Codecited by 2,004
  12. 2025Kimi k1.5: Scaling Reinforcement Learning with LLMscited by 1,210
7 more
  1. 2025Training Language Models to Reason Efficientlycited by 247
  2. 2023Secrets of RLHF in Large Language Models Part I: PPOcited by 229
  3. 2020What Matters In On-Policy Reinforcement Learning? A Large-Scale Empirical Studycited by 162
  4. 2025Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuningcited by 123
  5. 2024Can Language Models Learn to Skip Steps?cited by 59
  6. 2025AMO-Bench: Large Language Models Still Struggle in High School Math Competitionscited by 38
  7. 2025Toward Generalizable Evaluation in the LLM Era: A Survey Beyond Benchmarkscited by 28

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026DataRx: Missingness-Aware Sampling for Safer Large Language Model Task-Specific Fine-Tuningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025THOUGHTTERMINATOR: Benchmarking, Calibrating, and Mitigating Overthinking in Reasoning Models
  2. 2026Reasoning Quality Emerges Early: Data Curation for Reasoning Models
  3. 2025ReFIne: A Framework for Trustworthy Large Reasoning Models with Reliability, Faithfulness, and Interpretability
  4. 2026Knowing When Thinking Is Not Enough: Teaching Small Reasoning Models to Reason Beyond Their Parametric Knowledge
  5. 2026To Reason but Not to Stop: Understanding and Recovering Pruned Large Reasoning Models
  6. 2025DiffAdapt: Difficulty-Adaptive Reasoning for Token-Efficient LLM Inference
  7. 2026HintMR: Eliciting Stronger Mathematical Reasoning in Small Language Models
  8. 2025Concise Reasoning, Big Gains: Pruning Long Reasoning Trace with Difficulty-Aware Prompting