A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyond

Xiaoye Qu, Yafu Li, Zhaochen Su, Weigao Sun, Jianhao Yan, Dongrui Liu, Ganqu Cui, Daizong Liu, Shuxian Liang, Junxian He, Peng Li, Wei Wei, Jing Shao, Chaochao Lu, Yue Zhang, Xian-Sheng Hua, Bowen Zhou, Yu Cheng

Introduction

The landscape of Large Language Models (LLMs) is undergoing a fundamental shift from "System 1" thinking—fast, intuitive, next-token prediction—to "System 2" thinking, characterized by deliberate, multi-step reasoning. Models such as OpenAI’s o1 and DeepSeek-R1, known as Large Reasoning Models (LRMs), utilize extended Chain-of-Thought (CoT) processing to solve complex logical and mathematical problems. However, this increased capability comes at a significant computational cost. This survey explores the emerging field of efficient reasoning, categorizing the methods designed to maximize "intelligence per token" across the model lifecycle.

The Efficiency Crisis in Large Reasoning Models

While LRMs represent a leap in problem-solving ability, they are notoriously inefficient. The authors identify a "token economy" crisis where models often consume thousands of tokens to solve tasks that their non-reasoning counterparts handle in a fraction of the time. This inefficiency manifests in three primary patterns:

  1. Redundant Content: Models frequently repeat definitions or rephrase the initial query without advancing the logical state.
  2. Overthinking Simple Tasks: A reasoning model might generate hundreds of tokens to answer a trivial question like "What is the square of 3?"
  3. Suboptimal Paths: Models often "meander," falling into circular logic loops or switching between reasoning directions prematurely.
Comparison of generation lengths and reasoning verbosity between standard instruct models (Qwen2.5-32B-Instruct) and reasoning models (QwQ-32B).

As shown in the figure above, the QwQ-32B model can consume over 500 tokens for a simple arithmetic query that a standard instruct model resolves in 30. Statistically, the distribution of generation lengths for LRMs shows a massive shift toward higher token counts, illustrating the overhead currently required for "deliberation."

A Taxonomy of Efficiency Methods

To address these bottlenecks, researchers are developing strategies across four key stages of the model lifecycle:

1. Inference-Time Strategies

Inference-time methods aim to control the reasoning process dynamically. Length Budgeting (e.g., "Chain-of-Draft") forces models to use concise notations rather than full sentences. System Switching involves a controller that decides whether a query requires a "fast" System 1 response or a "slow" System 2 deliberation. Additionally, Parallel Search allows for generating multiple reasoning paths concurrently, pruning low-quality branches early to save total compute.

2. Supervised Fine-Tuning (SFT)

SFT focuses on training models on higher-quality, more concise data. Reasoning Chain Compression involves distilling verbose traces into dense, logical steps. A more radical approach is Latent-Space SFT, such as the Coconut framework, which moves reasoning from visible text tokens into hidden continuous representations. This allows the model to "think" internally without the latency of generating text tokens.

3. Reinforcement Learning (RL)

Standard RL often inadvertently rewards "length hacking," where longer chains are more likely to reach the correct answer by chance. To counter this, researchers are implementing Length-Aware Rewards that penalize excessive verbosity while rewarding logical correctness and brevity.

4. Pre-training and Architecture

At the architectural level, the goal is to overcome the quadratic cost of standard Transformers. This includes using Subquadratic Attention (like FlashAttention variants) or Linearization techniques that convert Transformers into more efficient structures like Mamba or State Space Models (SSMs).

Key Insights and Benchmarks

Efficiency is not merely about shortening responses; it is about reaching the "aha moment"—the core logical breakthrough—with minimal diversion. The survey highlights that "thinking in latent space" is one of the most promising frontiers, potentially offering orders-of-magnitude speedups for complex tasks.

To evaluate these methods, the authors point to specialized benchmarks like DNA Bench, which is specifically designed to expose the tendency of LRMs to produce excessively verbose reasoning chains. Traditional benchmarks like GSM8K and MATH-500 remain standard for measuring accuracy, but they are increasingly paired with efficiency metrics to assess the cost of that accuracy.

Future Directions and Limitations

Despite progress, significant challenges remain. Multimodal Inefficiency is a major hurdle; current LRMs often struggle with visual reasoning, leading to even more convoluted and circular paths than text-only tasks. Furthermore, there is no standard metric for the "utility" of an individual reasoning step, making it difficult to determine which tokens are truly necessary.

As we move toward "System 1.x" models—which intelligently allocate a thinking budget based on query difficulty—the focus will shift from simply scaling tokens to scaling the density of intelligence within those tokens.

Summary updated

Abstract

Recent Large Reasoning Models (LRMs), such as DeepSeek-R1 and OpenAI o1, have demonstrated strong performance gains by scaling up the length of Chain-of-Thought (CoT) reasoning during inference. However, a growing concern lies in their tendency to produce excessively long reasoning traces, which are often filled with redundant content (e.g., repeated definitions), over-analysis of simple problems, and superficial exploration of multiple reasoning paths for harder tasks. This inefficiency introduces significant challenges for training, inference, and real-world deployment (e.g., in agent-based systems), where token economy is critical. In this survey, we provide a comprehensive overview of recent efforts aimed at improving reasoning efficiency in LRMs, with a particular focus on the unique challenges that arise in this new paradigm. We identify common patterns of inefficiency, examine methods proposed across the LRM lifecycle, i.e., from pretraining to inference, and discuss promising future directions for research. To support ongoing development, we also maintain a real-time GitHub repository tracking recent progress in the field. We hope this survey serves as a foundation for further exploration and inspires innovation in this rapidly evolving area.
BibTeX
@misc{qu2025survey,
  author = {Xiaoye Qu and Yafu Li and Zhaochen Su and Weigao Sun and Jianhao Yan and Dongrui Liu and Ganqu Cui and Daizong Liu and Shuxian Liang and Junxian He and Peng Li and Wei Wei and Jing Shao and Chaochao Lu and Yue Zhang and Xian-Sheng Hua and Bowen Zhou and Yu Cheng},
  title = {{A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyond}},
  year = {2025},
  eprint = {2503.21614},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2503.21614},
}
Figure