# Can Pruning Improve Reasoning? Revisiting Long-CoT Compression with Capability in Mind for Better Reasoning

arXiv: https://arxiv.org/abs/2505.14582 · HTML: https://mlsanity.com/paper/2505.14582/

## Key facts

- Cited by 19 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 23 of its 41 references that are in the map.
- First posted on arXiv 20 May 2025.

## Placed in

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

## Builds on (most cited first, 23 of 23)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge](https://mlsanity.com/paper/1811.00937/) (2018)
- [Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them](https://mlsanity.com/paper/2210.09261/) (2022)
- [LIMO: Less is More for Reasoning](https://mlsanity.com/paper/2502.03387/) (2025)
- [Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models](https://mlsanity.com/paper/2503.09567/) (2025)
- [SWIFT:A Scalable lightWeight Infrastructure for Fine-Tuning](https://mlsanity.com/paper/2408.05517/) (2024)
- [LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression](https://mlsanity.com/paper/2403.12968/) (2024)
- [Demystifying Long Chain-of-Thought Reasoning in LLMs](https://mlsanity.com/paper/2502.03373/) (2025)
- [O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning](https://mlsanity.com/paper/2501.12570/) (2025)
- [When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning Method](https://mlsanity.com/paper/2402.17193/) (2024)
- [Distilling Reasoning Capabilities into Smaller Language Models](https://mlsanity.com/paper/2212.00193/) (2022)
- [Small Models Struggle to Learn from Strong Reasoners](https://mlsanity.com/paper/2502.12143/) (2025)
- [LightThinker: Thinking Step-by-Step Compression](https://mlsanity.com/paper/2502.15589/) (2025)
- [PRISM: Self-Pruning Intrinsic Selection Method for Training-Free Multimodal Data Selection](https://mlsanity.com/paper/2502.12119/) (2025)
- [Beyond Examples: High-level Automated Reasoning Paradigm in In-Context Learning via MCTS](https://mlsanity.com/paper/2411.18478/) (2024)
- [Deconstructing Long Chain-of-Thought: A Structured Reasoning Optimization Framework for Long CoT Distillation](https://mlsanity.com/paper/2503.16385/) (2025)
- [RATT: A Thought Structure for Coherent and Correct LLM Reasoning](https://mlsanity.com/paper/2406.02746/) (2024)
- [CoMT: Chain-of-Medical-Thought Reduces Hallucination in Medical Report Generation](https://mlsanity.com/paper/2406.11451/) (2024)
- [Markov Chain of Thought for Efficient Mathematical Reasoning](https://mlsanity.com/paper/2410.17635/) (2024)
- [Adaptive Graph of Thoughts: Test-Time Adaptive Reasoning Unifying Chain, Tree, and Graph Structures](https://mlsanity.com/paper/2502.05078/) (2025)
- [Learn Beyond The Answer: Training Language Models with Reflection for Mathematical Reasoning](https://mlsanity.com/paper/2406.12050/) (2024)
- [Self-Correction Makes LLMs Better Parsers](https://mlsanity.com/paper/2504.14165/) (2025)

## Built on by (most cited first, 19 of 19)

- [A Survey of Context Engineering for Large Language Models](https://mlsanity.com/paper/2507.13334/) (2025)
- [Reducing Cost of LLM Agents with Trajectory Reduction](https://mlsanity.com/paper/2509.23586/) (2025)
- [Don't Overthink It: A Survey of Efficient R1-style Large Reasoning Models](https://mlsanity.com/paper/2508.02120/) (2025)
- [Every Rollout Counts: Optimal Resource Allocation for Efficient Test-Time Scaling](https://mlsanity.com/paper/2506.15707/) (2025)
- [Neural Chain-of-Thought Search: Searching the Optimal Reasoning Path to Enhance Large Language Models](https://mlsanity.com/paper/2601.11340/) (2026)
- [PEAR: Phase Entropy Aware Reward for Efficient Reasoning](https://mlsanity.com/paper/2510.08026/) (2025)
- [Characterizing, Evaluating, and Optimizing Complex Reasoning](https://mlsanity.com/paper/2602.08498/) (2026)
- [SDEval: Safety Dynamic Evaluation for Multimodal Large Language Models](https://mlsanity.com/paper/2508.06142/) (2025)
- [SatireDecoder: Visual Cascaded Decoupling for Enhancing Satirical Image Comprehension](https://mlsanity.com/paper/2512.00582/) (2025)
- [Reinforcement Learning for Chain of Thought Compression with One-Domain-to-All Generalization](https://mlsanity.com/paper/2601.06052/) (2025)
- [Chopping Trees: Semantic Similarity Based Dynamic Pruning for Tree-of-Thought Reasoning](https://mlsanity.com/paper/2511.08595/) (2025)
- [STOP: Structured On-Policy Pruning of Long-Form Reasoning in Low-Data Regimes](https://mlsanity.com/paper/2605.13165/) (2026)
- [Mapping Text to Multiplex Graph: Prompt Compression as L'evy Walk-Guided Graph Pruning](https://mlsanity.com/paper/2607.01241/) (2026)
- [Bridging Efficiency and Transparency: Explainable CoT Compression in Multimodal Large Reasoning Models](https://mlsanity.com/paper/2602.09485/) (2026)
- [LegalDrill: Diagnosis-Driven Synthesis for Legal Reasoning in Small Language Models](https://mlsanity.com/paper/2604.23809/) (2026)
- [Breaking the Reward Barrier: Accelerating Tree-of-Thought Reasoning via Speculative Exploration](https://mlsanity.com/paper/2605.10195/) (2026)
- [When Compression Helps and When It Hurts: Condition-Aware Analysis of Chain-of-Thought Distillation](https://mlsanity.com/paper/2606.21704/) (2026)
- [Can Reasoning Models Detect Changes to their Chains of Thought?](https://mlsanity.com/paper/2606.22085/) (2026)
- [VIG: Visual Information Gain as a Reward Signal for Multimodal Chain-of-Thought Compression](https://mlsanity.com/paper/2608.21883/) (2026)

## Abstract (arXiv)

Long chain-of-thought (Long-CoT) reasoning improves accuracy in LLMs, yet its verbose, self-reflective style often hinders effective distillation into small language models (SLMs). We revisit Long-CoT compression through the lens of capability alignment and ask: Can pruning improve reasoning? We propose Prune-on-Logic, a structure-aware framework that transforms Long-CoT into logic graphs and selectively prunes low-utility reasoning steps under self-verification constraints. Through systematic analysis across three pruning strategies targeting entire chains, core reasoning, and verification, we find that verification pruning consistently improves accuracy while reducing token usage, whereas pruning reasoning steps or indiscriminate pruning degrades performance. Our study reveals that effective pruning aligns supervision with model capacity rather than merely shortening inputs. Gains hold across tasks, model scales, and CoT capability, with larger models benefiting more from pruning due to richer but more redundant reasoning. Our empirical findings highlight pruning as a structural optimization strategy for aligning CoT reasoning with SLM capacity.