# The Art of Efficient Reasoning: Data, Reward, and Optimization

arXiv: https://arxiv.org/abs/2602.20945 · HTML: https://mlsanity.com/paper/2602.20945/

## Key facts

- Cited by 4 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 34 references that are in the map.
- First posted on arXiv 24 Feb 2026.

## 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)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (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)
- [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://mlsanity.com/paper/2408.03314/) (2024)
- [Kimi k1.5: Scaling Reinforcement Learning with LLMs](https://mlsanity.com/paper/2501.12599/) (2025)
- [Training Large Language Models to Reason in a Continuous Latent Space](https://mlsanity.com/paper/2412.06769/) (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)
- [TokenSkip: Controllable Chain-of-Thought Compression in LLMs](https://mlsanity.com/paper/2502.12067/) (2025)
- [ThinkPrune: Pruning Long Chain-of-Thought of LLMs via Reinforcement Learning](https://mlsanity.com/paper/2504.01296/) (2025)
- [When More is Less: Understanding Chain-of-Thought Length in LLMs](https://mlsanity.com/paper/2502.07266/) (2025)
- [CoT-Valve: Length-Compressible Chain-of-Thought Tuning](https://mlsanity.com/paper/2502.09601/) (2025)
- [DAST: Difficulty-Adaptive Slow-Thinking for Large Reasoning Models](https://mlsanity.com/paper/2503.04472/) (2025)
- [Efficient Reasoning Models: A Survey](https://mlsanity.com/paper/2504.10903/) (2025)
- [Token Assorted: Mixing Latent and Text Tokens for Improved Language Model Reasoning](https://mlsanity.com/paper/2502.03275/) (2025)
- [Learn to Reason Efficiently with Adaptive Length-based Reward Shaping](https://mlsanity.com/paper/2505.15612/) (2025)
- [Prosperity before Collapse: How Far Can Off-Policy RL Reach with Stale Data on LLMs?](https://mlsanity.com/paper/2510.01161/) (2025)
- [Optimizing Anytime Reasoning via Budget Relative Policy Optimization](https://mlsanity.com/paper/2505.13438/) (2025)
- [Low-probability Tokens Sustain Exploration in Reinforcement Learning with Verifiable Reward](https://mlsanity.com/paper/2510.03222/) (2025)
- [Highly Efficient Self-Adaptive Reward Shaping for Reinforcement Learning](https://mlsanity.com/paper/2408.03029/) (2024)
- [φ-Decoding: Adaptive Foresight Sampling for Balanced Inference-Time Exploration and Exploitation](https://mlsanity.com/paper/2503.13288/) (2025)
- [Revisiting Model Interpolation for Efficient Reasoning](https://mlsanity.com/paper/2510.10977/) (2025)
- [DeepCompress: A Dual Reward Strategy for Dynamically Exploring and Compressing Reasoning Chains](https://mlsanity.com/paper/2510.27419/) (2025)

## Built on by (most cited first, 4 of 4)

- [HMPO: Hybrid Median-length Policy Optimization for Chain-of-Thought Compression](https://mlsanity.com/paper/2606.01934/) (2026)
- [CLORE: Content-Level Optimization for Reasoning Efficiency](https://mlsanity.com/paper/2605.22211/) (2026)
- [Lightning Weave: Improving the Accuracy-Efficiency Frontier of Reasoning Models through Capability Composition](https://mlsanity.com/paper/2609.14708/) (2026)
- [Lifted State Policy Optimization: Internalizing Self-Correction through Transition Geometry](https://mlsanity.com/paper/2610.20350/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) consistently benefit from scaled Chain-of-Thought (CoT) reasoning, but also suffer from heavy computational overhead. To address this issue, efficient reasoning aims to incentivize short yet accurate thinking trajectories, typically through reward shaping with Reinforcement Learning (RL). In this paper, we systematically investigate the mechanics of efficient reasoning for LLMs. For comprehensive evaluation, we advocate for more fine-grained metrics, including length distribution conditioned on correctness and performance across a wide spectrum of token budgets ranging from 2k to 32k. First, we reveal that the training process follows a two-stage paradigm: length adaptation and reasoning refinement. Through extensive experiments (about 0.2 million GPU hours) in a unified protocol, we deconstruct training prompts and rollouts, reward shaping, and optimization strategies. A central finding is to maintain a sufficient density of positive reward signals and avoid the short-is-correct trap. Moreover, the learned length bias generalizes across domains and difficulty levels. We distill these findings into valuable insights and practical guidelines, and validate them across the Qwen3 models ranging from 0.6B to 30B, demonstrating the robustness and generalization. Weights are available at https://wutaiqiang.github.io/project/Art