# Deconstructing Long Chain-of-Thought: A Structured Reasoning Optimization Framework for Long CoT Distillation

arXiv: https://arxiv.org/abs/2503.16385 · HTML: https://mlsanity.com/paper/2503.16385/

## Key facts

- Cited by 43 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 13 of its 22 references that are in the map.
- First posted on arXiv 20 Mar 2025.

## Placed in

- LLM reasoning / [Prompting and chain-of-thought reasoning](https://mlsanity.com/lr/prompting-and-chain-of-thought-reasoning/)

## Builds on (most cited first, 13 of 13)

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [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)
- [Kimi k1.5: Scaling Reinforcement Learning with LLMs](https://mlsanity.com/paper/2501.12599/) (2025)
- [Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate](https://mlsanity.com/paper/2305.19118/) (2023)
- [Large Language Monkeys: Scaling Inference Compute with Repeated Sampling](https://mlsanity.com/paper/2407.21787/) (2024)
- [Show Your Work: Scratchpads for Intermediate Computation with Language Models](https://mlsanity.com/paper/2112.00114/) (2021)
- [Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs](https://mlsanity.com/paper/2412.21187/) (2024)
- [When Can LLMs Actually Correct Their Own Mistakes? A Critical Survey of Self-Correction of LLMs](https://mlsanity.com/paper/2406.01297/) (2024)
- [O1 Replication Journey: A Strategic Progress Report -- Part 1](https://mlsanity.com/paper/2410.18982/) (2024)
- [O1 Replication Journey -- Part 2: Surpassing O1-preview through Simple Distillation, Big Progress or Bitter Lesson?](https://mlsanity.com/paper/2411.16489/) (2024)
- [Enhancing LLM Reasoning with Reward-guided Tree Search](https://mlsanity.com/paper/2411.11694/) (2024)
- [Scaling of Search and Learning: A Roadmap to Reproduce o1 from Reinforcement Learning Perspective](https://mlsanity.com/paper/2412.14135/) (2024)

## Built on by (most cited first, 30 of 43)

- [Dynamic Early Exit in Reasoning Models](https://mlsanity.com/paper/2504.15895/) (2025)
- [A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyond](https://mlsanity.com/paper/2503.21614/) (2025)
- [Efficient Reasoning Models: A Survey](https://mlsanity.com/paper/2504.10903/) (2025)
- [Purified OPSD: On-Policy Self-Distillation Without Losing How to Think](https://mlsanity.com/paper/2607.02234/) (2026)
- [System-1.5 Reasoning: Traversal in Language and Latent Spaces with Dynamic Shortcuts](https://mlsanity.com/paper/2505.18962/) (2025)
- [Can Pruning Improve Reasoning? Revisiting Long-CoT Compression with Capability in Mind for Better Reasoning](https://mlsanity.com/paper/2505.14582/) (2025)
- [Concise Reasoning, Big Gains: Pruning Long Reasoning Trace with Difficulty-Aware Prompting](https://mlsanity.com/paper/2505.19716/) (2025)
- [Are Large Language Models Reliable AI Scientists? Assessing Reverse-Engineering of Black-Box Systems](https://mlsanity.com/paper/2505.17968/) (2025)
- [Test-time Prompt Intervention](https://mlsanity.com/paper/2508.02511/) (2025)
- [Learning from Diverse Reasoning Paths with Routing and Collaboration](https://mlsanity.com/paper/2508.16861/) (2025)
- [Beyond Scaling Law: A Data-Efficient Distillation Framework for Reasoning](https://mlsanity.com/paper/2508.09883/) (2025)
- [Supervised Reinforcement Learning: From Expert Trajectories to Step-wise Reasoning](https://mlsanity.com/paper/2510.25992/) (2025)
- [Is More Privileged Information Better? From Solution Traces to Problem-Solving Structure in Self-Distilled Reasoning](https://mlsanity.com/paper/2608.01589/) (2026)
- [Incentivizing Strong Reasoning from Weak Supervision](https://mlsanity.com/paper/2505.20072/) (2025)
- [LayoutCoT: Unleashing the Deep Reasoning Potential of Large Language Models for Layout Generation](https://mlsanity.com/paper/2504.10829/) (2025)
- [Merge-of-Thought Distillation](https://mlsanity.com/paper/2509.08814/) (2025)
- [From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI](https://mlsanity.com/paper/2606.14502/) (2026)
- [Path Drift in Large Reasoning Models:How First-Person Commitments Override Safety](https://mlsanity.com/paper/2510.10013/) (2025)
- [CoT-Evo: Evolutionary Distillation of Chain-of-Thought for Scientific Reasoning](https://mlsanity.com/paper/2510.13166/) (2025)
- [Chain Of Thought Compression: A Theoretical Analysis](https://mlsanity.com/paper/2601.21576/) (2026)
- [Training-Trajectory-Aware Token Selection](https://mlsanity.com/paper/2601.10348/) (2026)
- [Efficient Reasoning with Balanced Thinking](https://mlsanity.com/paper/2603.12372/) (2026)
- [Reinforcement Learning for Chain of Thought Compression with One-Domain-to-All Generalization](https://mlsanity.com/paper/2601.06052/) (2025)
- [Stop When Further Reasoning Won't Help: Attention-State Adaptive Generation in Reasoning Models](https://mlsanity.com/paper/2606.15070/) (2026)
- [Beyond Templates: Dynamic Adaptation of Reasoning Demonstrations via Feasibility-Aware Exploration](https://mlsanity.com/paper/2505.20700/) (2025)
- [The Valley of Code Reasoning: Scaling Knowledge Distillation of Large Language Models](https://mlsanity.com/paper/2510.06101/) (2025)
- [Investigating Thinking Behaviours of Reasoning-Based Language Models for Social Bias Mitigation](https://mlsanity.com/paper/2510.17062/) (2025)
- [Offline Exploration-Aware Fine-Tuning for Long-Chain Mathematical Reasoning](https://mlsanity.com/paper/2603.16206/) (2026)
- [Amplify Adjacent Token Differences: Enhancing Long Chain-of-Thought Reasoning with Shift-FFN](https://mlsanity.com/paper/2505.17153/) (2025)
- [TRUST: A Decentralized Framework for Auditing Large Language Model Reasoning](https://mlsanity.com/paper/2510.20188/) (2025)

## Abstract (arXiv)

Recent advancements in large language models (LLMs) have demonstrated remarkable reasoning capabilities through long chain-of-thought (CoT) reasoning. The R1 distillation scheme has emerged as a promising approach for training cost-effective models with enhanced reasoning abilities. However, the underlying mechanisms driving its effectiveness remain unclear. This study examines the universality of distillation data and identifies key components that enable the efficient transfer of long-chain reasoning capabilities in LLM distillation. Our findings reveal that the effectiveness of long CoT reasoning distillation from teacher models like Qwen-QwQ degrades significantly on nonhomologous models, challenging the assumed universality of current distillation methods. To gain deeper insights into the structure and patterns of long CoT reasoning, we propose DLCoT (Deconstructing Long Chain-of-Thought), a distillation data enhancement framework. DLCoT consists of three key steps: (1) data segmentation to decompose complex long CoT structures, (2) simplification by eliminating unsolvable and redundant solutions, and (3) optimization of intermediate error states. Our approach significantly improves model performance and token efficiency, facilitating the development of high-performance LLMs.