A Short Survey on Small Reasoning Models: Training, Inference, Applications and Research Directions

Chengyu Wang, Taolin Zhang, Richang Hong, Jun HuangarXiv 2025 · DOI · arXiv

Introduction

The recent success of Large Reasoning Models (LRMs) like OpenAI’s o1 and DeepSeek-R1 has demonstrated the power of "slow thinking"—long chain-of-thought reasoning—for solving complex mathematical, coding, and logical problems. However, the massive scale of these models (e.g., DeepSeek-R1 at 671B parameters) creates significant barriers for research and deployment. This survey reviews the emerging landscape of Small Reasoning Models (SRMs), typically under 10 billion parameters, which achieve comparable reasoning capabilities through efficient training and inference techniques.

Taxonomy of Small Reasoning Models

SRMs are categorized by their architectural focus, training pipelines, and inference strategies. The following figure provides a structured overview of the current SRM landscape, from training methodologies to domain-specific applications.

Taxonomy of Small Reasoning Models (SRMs) covering training, inference, and applications.

Training Methodologies and Datasets

To overcome parameter constraints, SRMs rely on sophisticated training pipelines:

  • Knowledge Distillation: This is currently the most effective strategy. SRMs use LRMs as teachers to generate high-quality, long-form reasoning trajectories. Datasets like OpenThoughts-114k and OpenR1-Math provide the necessary synthetic data for this process.
  • Supervised Fine-Tuning (SFT): Models are trained on Chain-of-Thought (CoT) data to force the explicit generation of intermediate steps.
  • Reinforcement Learning (RL): Beyond standard RLHF, SRMs benefit from Outcome Reward Supervision (checking the final answer) using efficient algorithms like Group Relative Policy Optimization (GRPO), and Process Reward Models (PRMs) that evaluate intermediate reasoning steps.

Inference-Time Scaling

A core insight of the survey is that "inference compute" can often compensate for model size. By allocating more time for a model to "think" during test time, a 7B model can outperform much larger counterparts. Key techniques include:

  • Advanced Prompting: Moving from simple CoT to Tree of Thoughts (ToT) or Self-Consistency (CoT-SC).
  • Search and Verification: Using Monte Carlo Tree Search (MCTS) or step-wise verifiers to iteratively explore and refine solution paths.
  • Agent-Based Reasoning: Employing multi-agent collaboration where different SRM agents debate or check each other's work.

Empirical Performance and Benchmark Parity

Aggregated community findings show that distilled SRMs are routinely matching or beating older, much larger models on reasoning benchmarks.

Performance comparison of DeepSeek-R1-Distill-Qwen-7B against GPT-4o and Claude-3.5-Sonnet across key reasoning benchmarks.

As illustrated above, the DeepSeek-R1-Distill-Qwen-7B model demonstrates exceptional performance, particularly in mathematics (AIME2024 and MATH-500), where it significantly outperforms frontier models like GPT-4o. It also remains highly competitive in coding (LiveCodeBench) and general reasoning (GPQA Diamond).

Domain-Specific Applications

SRMs are particularly effective when adapted to specialized domains. In healthcare, specialized models like Hippo-Mistral-7B have achieved 59.9% on MedQA, outperforming the 70B Meditron model. Similar successes are noted in finance (e.g., Bloomberg-related corpora) and law (e.g., ChatLaw), where narrow domain expertise is combined with distilled reasoning logic.

Limitations and Future Directions

While SRMs democratize high-end AI research, they face challenges such as limited capacity for "exploration" beyond their training data and the potential to inherit biases from their LRM teachers. Future research is focused on developing adaptive RL strategies that balance exploration within limited parameter budgets, low-resource learning, and optimizing multi-agent communication to reduce token overhead.

Summary updated

Abstract

Recently, the reasoning capabilities of large reasoning models (LRMs), such as DeepSeek-R1, have seen significant advancements through the slow thinking process. Despite these achievements, the substantial computational demands of LRMs present considerable challenges. In contrast, small reasoning models (SRMs), often distilled from larger ones, offer greater efficiency and can exhibit distinct capabilities and cognitive trajectories compared to LRMs. This work surveys around 170 recently published papers on SRMs for tackling various complex reasoning tasks. We review the current landscape of SRMs and analyze diverse training and inference techniques related to SRMs. Furthermore, we provide a comprehensive review of SRMs for domain-specific applications and discuss possible future research directions. This survey serves as an essential reference for researchers to leverage or develop SRMs for advanced reasoning functionalities with high efficiency.
BibTeX
@misc{wang2025short,
  author = {Chengyu Wang and Taolin Zhang and Richang Hong and Jun Huang},
  title = {{A Short Survey on Small Reasoning Models: Training, Inference, Applications and Research Directions}},
  year = {2025},
  eprint = {2504.09100},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2504.09100},
}
Figure