# Long-Short Chain-of-Thought Mixture Supervised Fine-Tuning Eliciting Efficient Reasoning in Large Language Models

arXiv: https://arxiv.org/abs/2505.03469 · HTML: https://mlsanity.com/paper/2505.03469/

## Key facts

- Cited by 39 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 26 of its 41 references that are in the map.
- First posted on arXiv 6 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, 26 of 26)

- [RouteLLM: Learning to Route LLMs with Preference Data](https://mlsanity.com/paper/2406.18665/) (2024)
- [Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs](https://mlsanity.com/paper/2412.21187/) (2024)
- [Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models](https://mlsanity.com/paper/2503.16419/) (2025)
- [L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning](https://mlsanity.com/paper/2503.04697/) (2025)
- [Demystifying Long Chain-of-Thought Reasoning in LLMs](https://mlsanity.com/paper/2502.03373/) (2025)
- [Chain of Draft: Thinking Faster by Writing Less](https://mlsanity.com/paper/2502.18600/) (2025)
- [O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning](https://mlsanity.com/paper/2501.12570/) (2025)
- [Chain of Thought Empowers Transformers to Solve Inherently Serial Problems](https://mlsanity.com/paper/2402.12875/) (2024)
- [A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well?](https://mlsanity.com/paper/2503.24235/) (2025)
- [Navigate through Enigmatic Labyrinth A Survey of Chain of Thought Reasoning: Advances, Frontiers and Future](https://mlsanity.com/paper/2309.15402/) (2023)
- [Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond](https://mlsanity.com/paper/2503.10460/) (2025)
- [Imitate, Explore, and Self-Improve: A Reproduction Report on Slow-thinking Reasoning Systems](https://mlsanity.com/paper/2412.09413/) (2024)
- [DAST: Difficulty-Adaptive Slow-Thinking for Large Reasoning Models](https://mlsanity.com/paper/2503.04472/) (2025)
- [O1 Replication Journey: A Strategic Progress Report -- Part 1](https://mlsanity.com/paper/2410.18982/) (2024)
- [C3oT: Generating Shorter Chain-of-Thought without Compromising Effectiveness](https://mlsanity.com/paper/2412.11664/) (2024)
- [Sketch-of-Thought: Efficient LLM Reasoning with Adaptive Cognitive-Inspired Sketching](https://mlsanity.com/paper/2503.05179/) (2025)
- [SciEval: A Multi-Level Large Language Model Evaluation Benchmark for Scientific Research](https://mlsanity.com/paper/2308.13149/) (2023)
- [O1 Replication Journey -- Part 2: Surpassing O1-preview through Simple Distillation, Big Progress or Bitter Lesson?](https://mlsanity.com/paper/2411.16489/) (2024)
- [An Empirical Study on Eliciting and Improving R1-like Reasoning Models](https://mlsanity.com/paper/2503.04548/) (2025)
- [Efficient Test-Time Scaling via Self-Calibration](https://mlsanity.com/paper/2503.00031/) (2025)
- [Think Twice: Enhancing LLM Reasoning by Scaling Multi-round Test-time Thinking](https://mlsanity.com/paper/2503.19855/) (2025)
- [100 Days After DeepSeek-R1: A Survey on Replication Studies and More Directions for Reasoning Language Models](https://mlsanity.com/paper/2505.00551/) (2025)
- [Thought Manipulation: External Thought Can Be Efficient for Large Reasoning Models](https://mlsanity.com/paper/2504.13626/) (2025)
- [MuMath-Code: Combining Tool-Use Large Language Models with Multi-perspective Data Augmentation for Mathematical Reasoning](https://mlsanity.com/paper/2405.07551/) (2024)
- [Efficient Reasoning for LLMs through Speculative Chain-of-Thought](https://mlsanity.com/paper/2504.19095/) (2025)
- [ARES: Alternating Reinforcement Learning and Supervised Fine-Tuning for Enhanced Multi-Modal Chain-of-Thought Reasoning Through Diverse AI Feedback](https://mlsanity.com/paper/2407.00087/) (2024)

## Built on by (most cited first, 30 of 39)

- [Learning When to Think: Shaping Adaptive Reasoning in R1-Style Models via Multi-Stage RL](https://mlsanity.com/paper/2505.10832/) (2025)
- [SwS: Self-aware Weakness-driven Problem Synthesis in Reinforcement Learning for LLM Reasoning](https://mlsanity.com/paper/2506.08989/) (2025)
- [Don't Overthink It: A Survey of Efficient R1-style Large Reasoning Models](https://mlsanity.com/paper/2508.02120/) (2025)
- [Reasoning on a Budget: A Survey of Adaptive and Controllable Test-Time Compute in LLMs](https://mlsanity.com/paper/2507.02076/) (2025)
- [Promoting Efficient Reasoning with Verifiable Stepwise Reward](https://mlsanity.com/paper/2508.10293/) (2025)
- [Mini-Omni-Reasoner: Token-Level Thinking-in-Speaking in Large Speech Models](https://mlsanity.com/paper/2508.15827/) (2025)
- [ARES: Multimodal Adaptive Reasoning via Difficulty-Aware Token-Level Entropy Shaping](https://mlsanity.com/paper/2510.08457/) (2025)
- [Concise Reasoning, Big Gains: Pruning Long Reasoning Trace with Difficulty-Aware Prompting](https://mlsanity.com/paper/2505.19716/) (2025)
- [From Efficiency to Adaptivity: A Deeper Look at Adaptive Reasoning in Large Language Models](https://mlsanity.com/paper/2511.10788/) (2025)
- [The First Impression Problem: Internal Bias Triggers Overthinking in Reasoning Models](https://mlsanity.com/paper/2505.16448/) (2025)
- [Neural Chain-of-Thought Search: Searching the Optimal Reasoning Path to Enhance Large Language Models](https://mlsanity.com/paper/2601.11340/) (2026)
- [From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI](https://mlsanity.com/paper/2606.14502/) (2026)
- [How Well Do Large Reasoning Models Translate? A Comprehensive Evaluation for Multi-Domain Machine Translation](https://mlsanity.com/paper/2505.19987/) (2025)
- [Learning to Ponder: Adaptive Reasoning in Latent Space](https://mlsanity.com/paper/2509.24238/) (2025)
- [PEAR: Phase Entropy Aware Reward for Efficient Reasoning](https://mlsanity.com/paper/2510.08026/) (2025)
- [One Token Embedding Is Enough to Deadlock Your Large Reasoning Model](https://mlsanity.com/paper/2510.15965/) (2025)
- [CaughtCheating: Is Your MLLM a Good Cheating Detective? Exploring the Boundary of Visual Perception and Reasoning](https://mlsanity.com/paper/2507.00045/) (2025)
- [Putting on the Thinking Hats: A Survey on Chain of Thought Fine-tuning from the Perspective of Human Reasoning Mechanism](https://mlsanity.com/paper/2510.13170/) (2025)
- [Rethinking Supervised Fine-Tuning: Emphasizing Key Answer Tokens for Improved LLM Accuracy](https://mlsanity.com/paper/2512.21017/) (2025)
- [ConPress: Learning Efficient Reasoning from Multi-Question Contextual Pressure](https://mlsanity.com/paper/2602.01472/) (2026)
- [The Imitation Game: Turing Machine Imitator is Length Generalizable Reasoner](https://mlsanity.com/paper/2507.13332/) (2025)
- [TrajSelector: Harnessing Latent Representations for Efficient and Effective Best-of-N in Large Reasoning Model](https://mlsanity.com/paper/2510.16449/) (2025)
- [ReEfBench: Quantifying the Reasoning Efficiency of LLMs](https://mlsanity.com/paper/2601.03550/) (2026)
- [Draft-Thinking: Learning Efficient Reasoning in Long Chain-of-Thought LLMs](https://mlsanity.com/paper/2603.00578/) (2026)
- [ReasonAlloc: Hierarchical Decoding-Time KV Cache Budget Allocation for Reasoning Models](https://mlsanity.com/paper/2606.11164/) (2026)
- [The Valley of Code Reasoning: Scaling Knowledge Distillation of Large Language Models](https://mlsanity.com/paper/2510.06101/) (2025)
- [Efficient Reasoning via Thought-Training and Thought-Free Inference](https://mlsanity.com/paper/2511.03408/) (2025)
- [Stop Unnecessary Reflection: Training LRMs for Efficient Reasoning with Adaptive Reflection and Length Coordinated Penalty](https://mlsanity.com/paper/2602.12113/) (2026)
- [Focused Chain-of-Thought: Efficient LLM Reasoning via Structured Input Information](https://mlsanity.com/paper/2511.22176/) (2025)
- [QA-Merging: Query-Adaptive Reasoning via Layer Selective Model Merging](https://mlsanity.com/paper/2601.03506/) (2026)

## Abstract (arXiv)

Recent advances in large language models have demonstrated that Supervised Fine-Tuning (SFT) with Chain-of-Thought (CoT) reasoning data distilled from large reasoning models (e.g., DeepSeek R1) can effectively transfer reasoning capabilities to non-reasoning models. However, models fine-tuned with this approach inherit the "overthinking" problem from teacher models, producing verbose and redundant reasoning chains during inference. To address this challenge, we propose Long-Short Chain-of-Thought Mixture Supervised Fine-Tuning (LS-Mixture SFT), which combines long CoT reasoning dataset with their short counterparts obtained through structure-preserved rewriting. Our experiments demonstrate that models trained using the LS-Mixture SFT method, compared to those trained with direct SFT, achieved an average accuracy improvement of 2.3% across various benchmarks while substantially reducing model response length by approximately 47.61%. This work offers an approach to endow non-reasoning models with reasoning capabilities through supervised fine-tuning while avoiding the inherent overthinking problems inherited from teacher models, thereby enabling efficient reasoning in the fine-tuned models.