mlsanityData to 14 Oct 2026

R1-Compress: Long Chain-of-Thought Compression via Chunk Compression and Search

arXiv 2505.16838 ↗First posted 22 May 2025cs.CLcited by 30

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

Abstract (arXiv)

Chain-of-Thought (CoT) reasoning enhances large language models (LLMs) by enabling step-by-step problem-solving, yet its extension to Long-CoT introduces substantial computational overhead due to increased token length. Existing compression approaches -- instance-level and token-level -- either sacrifice essential local reasoning signals like reflection or yield incoherent outputs. To address these limitations, we propose R1-Compress, a two-stage chunk-level compression framework that preserves both local information and coherence. Our method segments Long-CoT into manageable chunks, applies LLM-driven inner-chunk compression, and employs an inter-chunk search mechanism to select the short and coherent sequence. Experiments on Qwen2.5-Instruct models across MATH500, AIME24, and GPQA-Diamond demonstrate that R1-Compress significantly reduces token usage while maintaining comparable reasoning accuracy. On MATH500, R1-Compress achieves an accuracy of 92.4%, with only a 0.6% drop compared to the Long-CoT baseline, while reducing token usage by about 20%. Source code will be available at https://github.com/w-yibo/R1-Compress

Key facts. Cited by 30 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 34 of its 44 references that are in the map. First posted on arXiv 22 May 2025.

Builds on

34 of 44 references.

Closest ancestors · 23

Same direction, newest first

  1. 2025Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning17 May
  2. 2025Adaptive GoGI-Skip: Coupling Goal-Gradient Importance with Dynamic Uncertainty for Efficient Reasoning13 May
  3. 2025ConCISE: Confidence-guided Compression in Step-by-step Efficient Reasoning8 May
  4. 2025Dynamic Early Exit in Reasoning Models22 Apr
  5. 2025Learning Adaptive Parallel Reasoning with Language Models21 Apr
  6. 2025Sleep-time Compute: Beyond Inference Scaling at Test-time17 Apr
  7. 2025Reasoning Models Can Be Effective Without Thinking14 Apr
  8. 2025Speculative Thinking: Enhancing Small-Model Reasoning with Large Model Guidance at Inference Time12 Apr
  9. 2025SEAL: Steerable Reasoning Calibration of Large Language Models for Free7 Apr
  10. 2025ThinkPrune: Pruning Long Chain-of-Thought of LLMs via Reinforcement Learning2 Apr
  11. 2025Harnessing the Reasoning Economy: A Survey of Efficient Reasoning for Large Language Models31 Mar
  12. 2025Efficient Inference for Large Reasoning Models: A Survey29 Mar
11 more
  1. 2025A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyond27 Mar
  2. 2025Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models20 Mar
  3. 2025Self-Training Elicits Concise Reasoning in Large Language Models27 Feb
  4. 2025LightThinker: Thinking Step-by-Step Compression21 Feb
  5. 2025TokenSkip: Controllable Chain-of-Thought Compression in LLMs17 Feb
  6. 2025CoT-Valve: Length-Compressible Chain-of-Thought Tuning13 Feb
  7. 2025O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning22 Jan
  8. 2024Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs30 Dec
  9. 2024Compressed Chain of Thought: Efficient Reasoning Through Dense Representations17 Dec
  10. 2024C3oT: Generating Shorter Chain-of-Thought without Compromising Effectiveness16 Dec
  11. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Models17 May

Other references · 11

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  2. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  3. 2024Qwen2.5 Technical Reportcited by 4,942
  4. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,879
  5. 2024Training Large Language Models to Reason in a Continuous Latent Spacecited by 797
  6. 2024A Survey on Large Language Models for Code Generationcited by 658
  7. 2025From System 1 to System 2: A Survey of Reasoning Large Language Modelscited by 320
  8. 2025Multimodal Chain-of-Thought Reasoning: A Comprehensive Surveycited by 182
  9. 2024Mulberry: Empowering MLLM with o1-like Reasoning and Reflection via Collective Monte Carlo Tree Searchcited by 175
  10. 2025Think When You Need: Self-Adaptive Chain-of-Thought Learningcited by 38
  11. 2025Ada-R1: Hybrid-CoT via Bi-Level Adaptive Reasoning Optimizationcited by 33

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 7; 2026: 23.

30 papers.

Sort:

By area:

  1. 2025Making Slow Thinking Faster: Compressing LLM Chain-of-Thought via Step Entropycited by 38
  2. 2025Don't Overthink It: A Survey of Efficient R1-style Large Reasoning Modelscited by 37
  3. 2026Purified OPSD: On-Policy Self-Distillation Without Losing How to Thinkcited by 31
  4. 2025A Survey on Agentic Multimodal Large Language Modelscited by 23
  5. 2026Render-of-Thought: Rendering Textual Chain-of-Thought as Images for Visual Latent Reasoningcited by 20
  6. 2026MEMENTO: Teaching LLMs to Manage Their Own Contextcited by 18
  7. 2025DRPO: Efficient Reasoning via Decoupled Reward Policy Optimizationcited by 16
  8. 2025MMReason: An Open-Ended Multi-Modal Multi-Step Reasoning Benchmark for MLLMs Toward AGIcited by 14
  9. 2026Neural Chain-of-Thought Search: Searching the Optimal Reasoning Path to Enhance Large Language Modelscited by 8
  10. 2026VTC-R1: Vision-Text Compression for Efficient Long-Context Reasoningcited by 8
  11. 2025Merge-of-Thought Distillationcited by 7
  12. 2025Scaling Up, Speeding Up: A Benchmark of Speculative Decoding for Efficient LLM Test-Time Scalingcited by 6
18 more
  1. 2026Token Economics for LLM Agents: A Dual-View Study from Computing and Economicscited by 6
  2. 2026Training-Trajectory-Aware Token Selectioncited by 4
  3. 2026ConMax: Confidence-Maximizing Compression for Efficient Chain-of-Thought Reasoningcited by 2
  4. 2026Shorthand for Thought: Compressing LLM Reasoning via Entropy-Guided Supertokenscited by 2
  5. 2026EntroCoT: Enhancing Chain-of-Thought via Adaptive Entropy-Guided Segmentationcited by 1
  6. 2026A State-Transition Framework for Efficient LLM Reasoningcited by 1
  7. 2026Long Chain-of-Thought Compression via Fine-Grained Group Policy Optimizationcited by 1
  8. 2026CRISP: Compressing Redundancy in Chain-of-Thought via Intrinsic Saliency Pruningcited by 1
  9. 2026HyPER: Bridging Exploration and Exploitation for Scalable LLM Reasoning with Hypothesis Path Expansion and Reductioncited by 0
  10. 2026Bridging Efficiency and Transparency: Explainable CoT Compression in Multimodal Large Reasoning Modelscited by 0
  11. 2026Breaking the Reward Barrier: Accelerating Tree-of-Thought Reasoning via Speculative Explorationcited by 0
  12. 2026PathCal: State-Aware Reflection-Marker Calibration for Efficient Reasoningcited by 0
  13. 2026When Compression Helps and When It Hurts: Condition-Aware Analysis of Chain-of-Thought Distillationcited by 0
  14. 2026When LLMs Develop Languages: Symbolic Communication for Efficient Multi-Agent Reasoningcited by 0
  15. 2026LISA: Linear-Indexed Sparse Attention for Efficient Long-Context Reasoningcited by 0
  16. 2026ThinkReset: Learnable Intermediate Interface Construction for Bounded-Context Long-Horizon Reasoningcited by 0
  17. 2026VIG: Visual Information Gain as a Reward Signal for Multimodal Chain-of-Thought Compressioncited by 0
  18. 2026SYNLAT: Syntax-Aligned Text-Latent Compression for Chain-of-Thought Reasoningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Chain Of Thought Compression: A Theoretical Analysis
  2. 2026Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compression
  3. 2025Reasoning Path Compression: Compressing Generation Trajectories for Efficient LLM Reasoning
  4. 2025From Long to Lean: Performance-aware and Adaptive Chain-of-Thought Compression via Multi-round Refinement
  5. 2026Memory Augmentation Unlocks Efficient Chain-of-Thought Reasoning
  6. 2026CtrlCoT: Dual-Granularity Chain-of-Thought Compression for Controllable Reasoning
  7. 2025How Well do LLMs Compress Their Own Chain-of-Thought? A Token Complexity Approach
  8. 2024Expediting and Elevating Large Language Model Reasoning via Hidden Chain-of-Thought Decoding