# SmartThinker: Learning to Compress and Preserve Reasoning by Step-Level Length Control

arXiv: https://arxiv.org/abs/2507.04348 · HTML: https://mlsanity.com/paper/2507.04348/

## Key facts

- Cited by 7 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 25 of its 39 references that are in the map.
- First posted on arXiv 6 Jul 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, 25 of 25)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [DAPO: An Open-Source LLM Reinforcement Learning System at Scale](https://mlsanity.com/paper/2503.14476/) (2025)
- [LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://mlsanity.com/paper/2403.07974/) (2024)
- [Solving Quantitative Reasoning Problems with Language Models](https://mlsanity.com/paper/2206.14858/) (2022)
- [Understanding R1-Zero-Like Training: A Critical Perspective](https://mlsanity.com/paper/2503.20783/) (2025)
- [ZeRO: Memory Optimizations Toward Training Trillion Parameter Models](https://mlsanity.com/paper/1910.02054/) (2019)
- [OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems](https://mlsanity.com/paper/2402.14008/) (2024)
- [Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement](https://mlsanity.com/paper/2409.12122/) (2024)
- [RACE: Large-scale ReAding Comprehension Dataset From Examinations](https://mlsanity.com/paper/1704.04683/) (2017)
- [Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs](https://mlsanity.com/paper/2412.21187/) (2024)
- [LIMO: Less is More for Reasoning](https://mlsanity.com/paper/2502.03387/) (2025)
- [Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models](https://mlsanity.com/paper/2503.16419/) (2025)
- [Improve Mathematical Reasoning in Language Models by Automated Process Supervision](https://mlsanity.com/paper/2406.06592/) (2024)
- [Chain of Draft: Thinking Faster by Writing Less](https://mlsanity.com/paper/2502.18600/) (2025)
- [Training Language Models to Reason Efficiently](https://mlsanity.com/paper/2502.04463/) (2025)
- [The Surprising Effectiveness of Negative Reinforcement in LLM Reasoning](https://mlsanity.com/paper/2506.01347/) (2025)
- [The Danger of Overthinking: Examining the Reasoning-Action Dilemma in Agentic Tasks](https://mlsanity.com/paper/2502.08235/) (2025)
- [AdaptThink: Reasoning Models Can Learn When to Think](https://mlsanity.com/paper/2505.13417/) (2025)
- [A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyond](https://mlsanity.com/paper/2503.21614/) (2025)
- [Thinkless: LLM Learns When to Think](https://mlsanity.com/paper/2505.13379/) (2025)
- [OverThink: Slowdown Attacks on Reasoning LLMs](https://mlsanity.com/paper/2502.02542/) (2025)
- [GRPO-LEAD: A Difficulty-Aware Reinforcement Learning Approach for Concise Mathematical Reasoning in Language Models](https://mlsanity.com/paper/2504.09696/) (2025)
- [Ada-R1: Hybrid-CoT via Bi-Level Adaptive Reasoning Optimization](https://mlsanity.com/paper/2504.21659/) (2025)

## Built on by (most cited first, 7 of 7)

- [Stop When Enough: Adaptive Early-Stopping for Chain-of-Thought Reasoning](https://mlsanity.com/paper/2510.10103/) (2025)
- [Neural Chain-of-Thought Search: Searching the Optimal Reasoning Path to Enhance Large Language Models](https://mlsanity.com/paper/2601.11340/) (2026)
- [Stepwise Penalization for Length-Efficient Chain-of-Thought Reasoning](https://mlsanity.com/paper/2603.00296/) (2026)
- [Agentic Chain-of-Thought Steering for Efficient and Controllable LLM Reasoning](https://mlsanity.com/paper/2606.03965/) (2026)
- [SCOPE-RL: Optimizing Reasoning Paths Before and After Success](https://mlsanity.com/paper/2607.11506/) (2026)
- [LEAD: Length-Efficient Adaptive and Dynamic Reasoning for Large Language Models](https://mlsanity.com/paper/2605.09806/) (2026)
- [QLPO: Quadrant-weighted Sampling for Length-aware Policy Optimization](https://mlsanity.com/paper/2607.21793/) (2026)

## Abstract (arXiv)

Large reasoning models (LRMs) have exhibited remarkable reasoning capabilities through inference-time scaling, but this progress has also introduced considerable redundancy and inefficiency into their reasoning processes, resulting in substantial computational waste. Previous work has attempted to mitigate this issue by penalizing the overall length of generated samples during reinforcement learning (RL), with the goal of encouraging a more concise chains of thought. However, we observe that such global length penalty often lead to excessive compression of critical reasoning steps while preserving unnecessary details in simpler ones, yielding a suboptimal trade-off between accuracy and efficiency. To address this issue, we propose SmartThinker, a two-stage learnable framework designed to enable fine-grained control over the length of reasoning chains based on the importance of each individual step. In the first stage, SmartThinker adapts a reasoning model to a short-form reasoning mode through rejection sampling combined with supervised fine-tuning (SFT). In the second stage, SmartThinker applies Step-Level Length Control Policy Optimization (SCPO) to refine the model output distribution, which increases the proportion of length allocated to critical steps while reducing redundancy in less important ones. SCPO consists of four core components: an online importance estimator, a step-level length control reward function, a step-level generalized advantage estimation (S-GAE) and a difficulty-adaptive clipping strategy. Working in concert, these components enable SCPO to implement differentiated length control across reasoning steps. Empirical results across multiple reasoning benchmarks and various backbone models demonstrate that SmartThinker significantly reduces redundant reasoning while achieving comparable or even superior performance to existing methods.