# Test-time compute and efficient thinking

Area: [LLM reasoning](https://mlsanity.com/lr/index.md). HTML: https://mlsanity.com/lr/test-time-compute-and-efficient-thinking/

## Key facts

- Test-time compute and efficient thinking: 2,144 papers on arXiv since 2022 (data through 14 Oct 2026).
- 493 of its 2,144 mapped papers (23%) cite “Tree of Thoughts: Deliberate Problem Solving with Large Language Models” (2023, arXiv 2305.10601).
- 385 of its 2,144 mapped papers (18%) cite “Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters” (2024, arXiv 2408.03314).
- 134 new papers 17 Sep–14 Oct.

## Most cited here

- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023), cited by 493 papers here
- [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://mlsanity.com/paper/2408.03314/) (2024), cited by 385 papers here
- [s1: Simple test-time scaling](https://mlsanity.com/paper/2501.19393/) (2025), cited by 294 papers here
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023), cited by 284 papers here
- [Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs](https://mlsanity.com/paper/2412.21187/) (2024), cited by 270 papers here
- [Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models](https://mlsanity.com/paper/2503.16419/) (2025), cited by 237 papers here
- [L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning](https://mlsanity.com/paper/2503.04697/) (2025), cited by 216 papers here
- [O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning](https://mlsanity.com/paper/2501.12570/) (2025), cited by 177 papers here
- [TokenSkip: Controllable Chain-of-Thought Compression in LLMs](https://mlsanity.com/paper/2502.12067/) (2025), cited by 164 papers here
- [Dynamic Early Exit in Reasoning Models](https://mlsanity.com/paper/2504.15895/) (2025), cited by 147 papers here

## New (17 Sep–14 Oct)

- [LEV: Thinking Fast and Deep with Looped Decision Models](https://mlsanity.com/paper/2610.20951/) (2026-10-14)
- [Recursive Offline Distillation via Entropy Gain Sampling and Answer Mixing](https://mlsanity.com/paper/2610.20914/) (2026-10-14)
- [Confidence-Calibrated Inference Expansion for Evaluator-Guided Test-Time Reasoning](https://mlsanity.com/paper/2610.20836/) (2026-10-14)
- [Amortizing Sequential Experimental Design in Reasoning LLMs](https://mlsanity.com/paper/2610.20832/) (2026-10-14)
- [Decoupled Marginal Sharpening for Training-Free Inference-Time Scaling](https://mlsanity.com/paper/2610.20483/) (2026-10-14)
- [Beyond Correctness: Compute-Responsive Data Selection for Reasoning Model Post-Training](https://mlsanity.com/paper/2610.20057/) (2026-10-14)
- [To Reason but Not to Stop: Understanding and Recovering Pruned Large Reasoning Models](https://mlsanity.com/paper/2610.19934/) (2026-10-14)
- [MemDuet: Learning Dual-Process Memory for Long-Context Reasoning](https://mlsanity.com/paper/2610.19928/) (2026-10-14)
- [Frustratingly Easy Majority Voting Using Length Conditioning](https://mlsanity.com/paper/2610.19890/) (2026-10-14)
- [Rationale Distribution Distillation via Flow Matching for Distributional Continuous Latent Reasoning](https://mlsanity.com/paper/2610.19871/) (2026-10-14)
- [REWIND: Uncertainty-Guided Trajectory Repair for Test-Time Reasoning](https://mlsanity.com/paper/2610.19561/) (2026-10-14)
- [Tail Competition Explains Scaling in Best-of-N Sampling for Verifiable Problems](https://mlsanity.com/paper/2610.19362/) (2026-10-14)
- [Unlocking Structured Pruning for Reasoning Language Models via Attention-Preserving MLP Trimming](https://mlsanity.com/paper/2610.19121/) (2026-10-13)
- [DoubtLess: Training-Free Contrastive Decoding for Efficient Reasoning](https://mlsanity.com/paper/2610.18862/) (2026-10-13)
- [Compare to Correct: Pairwise-Guided Logit Adjustment for LLM Test-Time Scaling](https://mlsanity.com/paper/2610.18583/) (2026-10-13)
- [Input-Conditioned Search for Efficient Test-Time Scaling of Recursive Reasoners](https://mlsanity.com/paper/2610.18547/) (2026-10-13)
- [Efficient Safety Guardrails through Latent Dual-Hypothesis Reasoning with On-Demand Trace Reconstruction](https://mlsanity.com/paper/2610.18304/) (2026-10-13)
- [Monitoring latent reasoning in looped language models](https://mlsanity.com/paper/2610.18127/) (2026-10-13)
- [SHELDON: Reasoning through Dual Search over Hypothesis and Observation Spaces](https://mlsanity.com/paper/2610.18025/) (2026-10-13)
- [PaceReasoner: Label-Free Learning to Answer Briefly from Long Reasoning](https://mlsanity.com/paper/2610.17900/) (2026-10-13)
- [Efficiently Learning To Reason or Not to Reason: Root-token Policy Optimization for Adaptive Thinking](https://mlsanity.com/paper/2610.17767/) (2026-10-13)
- [Dynamic K-Head: Difficulty-Supervised Budget Selection for Continuous Latent Reasoning](https://mlsanity.com/paper/2610.17679/) (2026-10-13)
- [Soft Teacher Forcing](https://mlsanity.com/paper/2610.17189/) (2026-10-12)
- [Resample the Answer: Where to Spend Test-Time Compute in Recursive Reasoning](https://mlsanity.com/paper/2610.16427/) (2026-10-12)
- [DeepThink: A Conceptual Model for Knowledge-Addressable Recurrent Language Modeling](https://mlsanity.com/paper/2610.16171/) (2026-10-12)
- [Think Before You Speak: Enabling Training-Free Latent Communication Between Language Models](https://mlsanity.com/paper/2610.16165/) (2026-10-12)
- [From Candidate Tokens to Final Outcomes: Decoding Relative Long-Horizon Candidate Value from Reasoning Model Representations](https://mlsanity.com/paper/2610.15412/) (2026-10-11)
- [RECAP: Calibrating Low-Bit Reasoning Models on the History They Read](https://mlsanity.com/paper/2610.15259/) (2026-10-11)
- [Measuring the Inference Energy Efficiency of Open-Weight LLMs across Benchmarks, Reasoning Modes, and Hardware](https://mlsanity.com/paper/2610.14389/) (2026-10-09)
- [Inject a Turn, Not a Token: Learning Where to Redirect LLM Reasoning for Self-Correction](https://mlsanity.com/paper/2610.13672/) (2026-10-09)