mlsanityData to 14 Oct 2026

DTS: Enhancing Large Reasoning Models via Decoding Tree Sketching

arXiv 2511.00640 ↗First posted 1 Nov 2025cs.AI cs.CL cs.LGcited by 6

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

Abstract (arXiv)

Large Reasoning Models (LRMs) achieve remarkable inference-time improvements through parallel thinking. However, existing methods rely on redundant sampling of reasoning trajectories, failing to effectively explore the reasoning space to uncover high-quality solutions. To address these limitations, we propose Decoding Tree Sketching (DTS), a plug-and-play decoding framework for structural multi-trajectory exploration and reasoning selection. For reasoning exploration, DTS sketches a backbone tree of the reasoning space by selectively branching at decision tokens. For reasoning selection, guided by length-accuracy anti-correlation, DTS designs an early termination to prioritize short and reliable trajectories during decoding. Experimental results across four LRMs and datasets demonstrate that DTS significantly enhances accuracy by 14% and reduces repetitive generation by 8% on average. Notably, DTS enables smaller models to outperform larger models with 10× the size, highlighting its potential to strengthen reasoning capabilities.

Key facts. Cited by 6 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 50 of its 55 references that are in the map. First posted on arXiv 1 Nov 2025.

Builds on

50 of 55 references.

Closest ancestors · 17

Same direction, newest first

  1. 2025Trace Length is a Simple Uncertainty Signal in Reasoning Models12 Oct
  2. 2025PiCSAR: Probabilistic Confidence Selection And Ranking for Reasoning Chains29 Aug
  3. 2025Deep Think with Confidence21 Aug
  4. 2025ReCUT: Balancing Reasoning Length and Accuracy in LLMs via Stepwise Trails and Preference Optimization12 Jun
  5. 2025VeriThinker: Learning to Verify Makes Reasoning Model Efficient23 May
  6. 2025AdaptThink: Reasoning Models Can Learn When to Think19 May
  7. 2025AdaCoT: Pareto-Optimal Adaptive Chain-of-Thought Triggering via Reinforcement Learning17 May
  8. 2025ThinkPrune: Pruning Long Chain-of-Thought of LLMs via Reinforcement Learning2 Apr
  9. 2025Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models20 Mar
  10. 2025L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning6 Mar
  11. 2025DAST: Difficulty-Adaptive Slow-Thinking for Large Reasoning Models6 Mar
  12. 2025O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning22 Jan
5 more
  1. 2024Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs30 Dec
  2. 2024C3oT: Generating Shorter Chain-of-Thought without Compromising Effectiveness16 Dec
  3. 2024Concise Thoughts: Impact of Output Length on LLM Reasoning and Cost29 Jul
  4. 2024Self-Discover: Large Language Models Self-Compose Reasoning Structures6 Feb
  5. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Models17 May

Other references · 33

  1. 2022Training language models to follow instructions with human feedbackcited by 15,971
  2. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  4. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  5. 2025Qwen3 Technical Reportcited by 8,820
  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. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,720
  9. 2023Qwen Technical Reportcited by 3,344
  10. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,879
  11. 2016Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translationcited by 1,475
  12. 2025Understanding R1-Zero-Like Training: A Critical Perspectivecited by 1,345
21 more
  1. 2025Kimi k1.5: Scaling Reinforcement Learning with LLMscited by 1,210
  2. 2024Large Language Monkeys: Scaling Inference Compute with Repeated Samplingcited by 991
  3. 2023Reasoning with Language Model is Planning with World Modelcited by 861
  4. 2023Large Language Models Can Be Easily Distracted by Irrelevant Contextcited by 841
  5. 2024Phi-4 Technical Reportcited by 711
  6. 2024A Survey on Large Language Models for Code Generationcited by 658
  7. 2021Datasets: A Community Library for Natural Language Processingcited by 530
  8. 2025Chain of Draft: Thinking Faster by Writing Lesscited by 297
  9. 2024LiveBench: A Challenging, Contamination-Limited LLM Benchmarkcited by 262
  10. 2025A Survey of Reinforcement Learning for Large Reasoning Modelscited by 180
  11. 2024What Large Language Models Know and What People Think They Knowcited by 110
  12. 2024MAIN-RAG: Multi-Agent Filtering Retrieval-Augmented Generationcited by 44
  13. 2025Advancing Reasoning in Large Language Models: Promising Methods and Approachescited by 43
  14. 2025Understanding the Repeat Curse in Large Language Models from a Feature Perspectivecited by 37
  15. 2024Confidence Under the Hood: An Investigation into the Confidence-Probability Alignment in Large Language Modelscited by 34
  16. 2025Confident or Seek Stronger: Exploring Uncertainty-Based On-device LLM Routing From Benchmarking to Generalizationcited by 29
  17. 2025How Is LLM Reasoning Distracted by Irrelevant Context? An Analysis Using a Controlled Benchmarkcited by 28
  18. 2025Trust Me, I'm Wrong: LLMs Hallucinate with Certainty Despite Knowing the Answercited by 27
  19. 2024Assessing and Enhancing Large Language Models in Rare Disease Question-answeringcited by 16
  20. 2024CoMAT: Chain of Mathematically Annotated Thought Improves Mathematical Reasoningcited by 16
  21. 2025The Signal is in the Steps: Local Scoring for Reasoning Data Selectioncited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 6.

6 papers.

  1. 2026Conformal Thinking: Risk Control for Reasoning on a Compute Budgetcited by 10
  2. 2026SEER: Long-Context Reasoning via Selective Visual-Text Compressioncited by 3
  3. 2026Dissecting Failure Dynamics in Large Language Model Reasoningcited by 2
  4. 2026Learning at the Right Pace: Adaptive Data Scheduling Improves LLM Reinforcement Learningcited by 2
  5. 2026When Implausible Tokens Get Reinforced: Tail-Aware Credit Calibration for LLM Reinforcement Learningcited by 1
  6. 2026Frustratingly Easy Majority Voting Using Length Conditioningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026When LLM Meets Tree Search: A Systematic View of Inference as Search in Large Language Models
  2. 2026ThinkRouter: Efficient Reasoning via Routing Thinking between Latent and Discrete Spaces
  3. 2025From Long to Short: LLMs Excel at Trimming Own Reasoning Chains
  4. 2026Selective Regenerative Decoding: Trajectory-Level Intervention for Inference-Time Reasoning
  5. 2026TERMINATOR: Learning Optimal Exit Points for Early Stopping in Chain-of-Thought Reasoning
  6. 2025Tracing the Traces: Latent Temporal Signals for Efficient and Accurate Reasoning
  7. 2025ThinkBrake: Efficient Reasoning via Log-Probability Margin Guided Decoding
  8. 2025Encode, Think, Decode: Scaling test-time reasoning with recursive latent thoughts