# DRP: Distilled Reasoning Pruning with Skill-aware Step Decomposition for Efficient Large Reasoning Models

arXiv: https://arxiv.org/abs/2505.13975 · HTML: https://mlsanity.com/paper/2505.13975/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- Placed in Prompting and chain-of-thought reasoning, one of 17 directions in LLM reasoning.
- Builds on 20 of its 38 references that are in the map.
- First posted on arXiv 20 May 2025.

## Placed in

- LLM reasoning / [Prompting and chain-of-thought reasoning](https://mlsanity.com/lr/prompting-and-chain-of-thought-reasoning/)
- Knowledge distillation / [Knowledge distillation for LLMs](https://mlsanity.com/distill/knowledge-distillation-for-llms/)

## Builds on (most cited first, 20 of 20)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [s1: Simple test-time scaling](https://mlsanity.com/paper/2501.19393/) (2025)
- [Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs](https://mlsanity.com/paper/2412.21187/) (2024)
- [From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge](https://mlsanity.com/paper/2411.16594/) (2024)
- [Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models](https://mlsanity.com/paper/2503.16419/) (2025)
- [Dynamic Early Exit in Reasoning Models](https://mlsanity.com/paper/2504.15895/) (2025)
- [Large Language Models for Data Annotation and Synthesis: A Survey](https://mlsanity.com/paper/2402.13446/) (2024)
- [CoT-Valve: Length-Compressible Chain-of-Thought Tuning](https://mlsanity.com/paper/2502.09601/) (2025)
- [Human-like Summarization Evaluation with ChatGPT](https://mlsanity.com/paper/2304.02554/) (2023)
- [Preference Leakage: A Contamination Problem in LLM-as-a-judge](https://mlsanity.com/paper/2502.01534/) (2025)
- [Small Models Struggle to Learn from Strong Reasoners](https://mlsanity.com/paper/2502.12143/) (2025)
- [S-GRPO: Early Exit via Reinforcement Learning in Reasoning Models](https://mlsanity.com/paper/2505.07686/) (2025)
- [Revisiting the Test-Time Scaling of o1-like Models: Do they Truly Possess Test-Time Scaling Capabilities?](https://mlsanity.com/paper/2502.12215/) (2025)
- [Can LLMs Learn from Previous Mistakes? Investigating LLMs' Errors to Boost for Reasoning](https://mlsanity.com/paper/2403.20046/) (2024)
- [Chain-of-Reasoning: Towards Unified Mathematical Reasoning in Large Language Models via a Multi-Paradigm Perspective](https://mlsanity.com/paper/2501.11110/) (2025)
- [Stronger Models are NOT Stronger Teachers for Instruction Tuning](https://mlsanity.com/paper/2411.07133/) (2024)
- [TwT: Thinking without Tokens by Habitual Reasoning Distillation with Multi-Teachers' Guidance](https://mlsanity.com/paper/2503.24198/) (2025)

## Built on by (most cited first, 30 of 30)

- [Making Slow Thinking Faster: Compressing LLM Chain-of-Thought via Step Entropy](https://mlsanity.com/paper/2508.03346/) (2025)
- [Don't Overthink It: A Survey of Efficient R1-style Large Reasoning Models](https://mlsanity.com/paper/2508.02120/) (2025)
- [SCRIBE: Structured Mid-Level Supervision for Tool-Using Language Models](https://mlsanity.com/paper/2601.03555/) (2026)
- [Towards Concise and Adaptive Thinking in Large Reasoning Models: A Survey](https://mlsanity.com/paper/2507.09662/) (2025)
- [Semantic-Space Exploration and Exploitation in RLVR for LLM Reasoning](https://mlsanity.com/paper/2509.23808/) (2025)
- [When Safe Skills Collide: Measuring Compositional Risk in Agent Skill Ecosystems](https://mlsanity.com/paper/2606.00448/) (2026)
- [TL;DR: Too Long, Do Re-weighting for Efficient LLM Reasoning Compression](https://mlsanity.com/paper/2506.02678/) (2025)
- [Stop When Enough: Adaptive Early-Stopping for Chain-of-Thought Reasoning](https://mlsanity.com/paper/2510.10103/) (2025)
- [Learning How to Use Tools, Not Just When: Pattern-Aware Tool-Integrated Reasoning](https://mlsanity.com/paper/2509.23292/) (2025)
- [ToolPRMBench: Evaluating and Advancing Process Reward Models for Tool-using Agents](https://mlsanity.com/paper/2601.12294/) (2026)
- [Sustainable Hybrid Document-Routed Retrieval for Financial RAG: Resolving the Robustness-Precision Trade-off](https://mlsanity.com/paper/2603.26815/) (2026)
- [Bridging Reasoning Trajectories in On-Policy Distillation via Near-Future Guidance](https://mlsanity.com/paper/2606.00305/) (2026)
- [Cornerstones or Stumbling Blocks? Deciphering the Rock Tokens in On-Policy Distillation](https://mlsanity.com/paper/2605.09253/) (2026)
- [Neural Chain-of-Thought Search: Searching the Optimal Reasoning Path to Enhance Large Language Models](https://mlsanity.com/paper/2601.11340/) (2026)
- [Reason Only When Needed: Efficient Generative Reward Modeling via Model-Internal Uncertainty](https://mlsanity.com/paper/2604.10072/) (2026)
- [FROST: Filtering Reasoning Outliers with Attention for Efficient Reasoning](https://mlsanity.com/paper/2601.19001/) (2026)
- [ConPress: Learning Efficient Reasoning from Multi-Question Contextual Pressure](https://mlsanity.com/paper/2602.01472/) (2026)
- [DriftGuard: Safety-Aware Multi-Monitor Detection and Selective Adaptation for Evolving Toxicity Moderation](https://mlsanity.com/paper/2606.28725/) (2026)
- [MIS-HCC: Hierarchical Channel Clustering for Efficient Medical Image Segmentation](https://mlsanity.com/paper/2607.17329/) (2026)
- [MUSE: Resolving Manifold Misalignment in Visual Tokenization via Topological Orthogonality](https://mlsanity.com/paper/2605.05646/) (2026)
- [Same Question, Different Answer? Measuring and Mitigating Prompt Privilege for Equitable AI Access](https://mlsanity.com/paper/2608.08942/) (2026)
- [Adaptive Dual Reasoner: Large Reasoning Models Can Think Efficiently by Hybrid Reasoning](https://mlsanity.com/paper/2510.10207/) (2025)
- [Stop Unnecessary Reflection: Training LRMs for Efficient Reasoning with Adaptive Reflection and Length Coordinated Penalty](https://mlsanity.com/paper/2602.12113/) (2026)
- [TRiMS: Real-Time Tracking of Minimal Sufficient Length for Efficient Reasoning via RL](https://mlsanity.com/paper/2603.17449/) (2026)
- [Energy-Efficient On-Device RAG on a Mobile NPU: System Design and Benchmark on Snapdragon X Elite](https://mlsanity.com/paper/2606.11257/) (2026)
- [Graph-Based Chain-of-Thought Pruning for Reducing Redundant Reflections in Reasoning LLMs](https://mlsanity.com/paper/2604.05643/) (2026)
- [MOSAIC: Orchestrating Collaborative Knowledge Tracing with Hierarchical Semantic Alignment](https://mlsanity.com/paper/2606.29049/) (2026)
- [Toward Skill-Native LLMs: Skill Entropy for Benchmarking and Training Long-Horizon Reasoning](https://mlsanity.com/paper/2608.05139/) (2026)
- [DRT: Dense Reasoning Trace for Efficient and Grounded Multimodal Reasoning](https://mlsanity.com/paper/2609.21675/) (2026)
- [Progress-Aware Distillation for Mitigating Stagnation in Small Language Model Agents](https://mlsanity.com/paper/2610.19439/) (2026)

## Abstract (arXiv)

While Large Reasoning Models (LRMs) have demonstrated success in complex reasoning tasks through long chain-of-thought (CoT) reasoning, their inference often involves excessively verbose reasoning traces, resulting in substantial inefficiency. To address this, we propose Distilled Reasoning Pruning (DRP), a hybrid framework that combines inference-time pruning with tuning-based distillation, two widely used strategies for efficient reasoning. DRP uses a teacher model to perform skill-aware step decomposition and content pruning, and then distills the pruned reasoning paths into a student model, enabling it to reason both efficiently and accurately. Across several challenging mathematical reasoning datasets, we find that models trained with DRP achieve substantial improvements in token efficiency without sacrificing accuracy. Specifically, DRP reduces average token usage on GSM8K from 917 to 328 while improving accuracy from 91.7% to 94.1%, and achieves a 43% token reduction on AIME with no performance drop. Further analysis shows that aligning the reasoning structure of training CoTs with the student's reasoning capacity is critical for effective knowledge transfer and performance gains.