A Study on Thinking Patterns of Large Reasoning Models in Code Generation

• URL: http://arxiv.org/abs/2509.13758v1
• Date: Wed, 17 Sep 2025 07:13:12 GMT
• Title: A Study on Thinking Patterns of Large Reasoning Models in Code Generation
• Authors: Kevin Halim, Sin G. Teo, Ruitao Feng, Zhenpeng Chen, Yang Gu, Chong Wang, Yang Liu,
• Abstract summary: Large language models (LLMs) are utilized for software engineering tasks such as code generation.<n>This paper presents a comprehensive study aimed at investigating and uncovering the reasoning behavior of LRMs during code generation.<n>We derive a taxonomy of LRM reasoning behaviors, encompassing 15 reasoning actions across four phases.
• Score: 14.138043269602074
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Currently, many large language models (LLMs) are utilized for software engineering tasks such as code generation. The emergence of more advanced models known as large reasoning models (LRMs), such as OpenAI's o3, DeepSeek R1, and Qwen3. They have demonstrated the capability of performing multi-step reasoning. Despite the advancement in LRMs, little attention has been paid to systematically analyzing the reasoning patterns these models exhibit and how such patterns influence the generated code. This paper presents a comprehensive study aimed at investigating and uncovering the reasoning behavior of LRMs during code generation. We prompted several state-of-the-art LRMs of varying sizes with code generation tasks and applied open coding to manually annotate the reasoning traces. From this analysis, we derive a taxonomy of LRM reasoning behaviors, encompassing 15 reasoning actions across four phases. Our empirical study based on the taxonomy reveals a series of findings. First, we identify common reasoning patterns, showing that LRMs generally follow a human-like coding workflow, with more complex tasks eliciting additional actions such as scaffolding, flaw detection, and style checks. Second, we compare reasoning across models, finding that Qwen3 exhibits iterative reasoning while DeepSeek-R1-7B follows a more linear, waterfall-like approach. Third, we analyze the relationship between reasoning and code correctness, showing that actions such as unit test creation and scaffold generation strongly support functional outcomes, with LRMs adapting strategies based on task context. Finally, we evaluate lightweight prompting strategies informed by these findings, demonstrating the potential of context- and reasoning-oriented prompts to improve LRM-generated code. Our results offer insights and practical implications for advancing automatic code generation.

Related papers

• Step-Tagging: Toward controlling the generation of Language Reasoning Models through step monitoring [5.190961793309368]
  A growing body of studies show that Language Reasoning Models (LRMs) are still inefficient, over-generating verification and reflection steps.<n>We introduce the Step-Tagging framework, a lightweight sentence-classifier enabling real-time annotation of the type of reasoning steps that an LRM is generating.<n>Online monitoring of the count of specific steps can produce effective interpretable early stopping criteria of LRM inferences.
  arXiv  Detail & Related papers  (2025-12-16T12:01:16Z)
• Your thoughts tell who you are: Characterize the reasoning patterns of LRMs [31.313418571838152]
  We use a generative language model to compare reasoning traces from two LRMs and articulate their distinctive features in words.<n>Iterating this process over a dataset of reasoning traces yields a human-language taxonomy that characterizes how models think.<n>LOT identifies systematic differences in their thoughts, achieving 80-100% accuracy in distinguishing reasoning traces from LRMs that differ in scale, base model family, or objective domain.
  arXiv  Detail & Related papers  (2025-09-29T00:52:07Z)
• Teaching LLM to Reason: Reinforcement Learning from Algorithmic Problems without Code [76.80306464249217]
  We propose TeaR, which aims at teaching LLMs to reason better.<n>TeaR leverages careful data curation and reinforcement learning to guide models in discovering optimal reasoning paths through code-related tasks.<n>We conduct extensive experiments using two base models and three long-CoT distillation models, with model sizes ranging from 1.5 billion to 32 billion parameters, and across 17 benchmarks spanning Math, Knowledge, Code, and Logical Reasoning.
  arXiv  Detail & Related papers  (2025-07-10T07:34:05Z)
• On Reasoning Strength Planning in Large Reasoning Models [50.61816666920207]
  We find evidence that LRMs pre-plan the reasoning strengths in their activations even before generation.<n>We then uncover that LRMs encode this reasoning strength through a pre-allocated directional vector embedded in the activations of the model.<n>Our work provides new insights into the internal mechanisms of reasoning in LRMs and offers practical tools for controlling their reasoning behaviors.
  arXiv  Detail & Related papers  (2025-06-10T02:55:13Z)
• The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity [16.266145641151375]
  Large Reasoning Models generate detailed thinking processes before providing answers.<n>We show that LRMs face a complete accuracy collapse beyond certain complexities.<n>We also investigate the reasoning traces in more depth, studying the patterns of explored solutions.
  arXiv  Detail & Related papers  (2025-06-07T22:42:29Z)
• Efficient Inference for Large Reasoning Models: A Survey [74.17203483365171]
  Large Reasoning Models (LRMs) significantly improve the reasoning ability of Large Language Models (LLMs) by learning to reason.<n>However, their deliberative reasoning process leads to inefficiencies in token usage, memory consumption, and inference time.<n>This survey provides a review of efficient inference methods designed specifically for LRMs, focusing on mitigating token inefficiency while preserving the reasoning quality.
  arXiv  Detail & Related papers  (2025-03-29T13:27:46Z)
• ReaRAG: Knowledge-guided Reasoning Enhances Factuality of Large Reasoning Models with Iterative Retrieval Augmented Generation [38.64751082999587]
  Large Reasoning Models (LRMs) exhibit remarkable reasoning abilities but rely primarily on parametric knowledge, limiting factual accuracy.<n>We propose ReaRAG, a factuality-enhanced reasoning model that explores diverse queries without excessive iterations.<n>Our study enhances LRMs' factuality while effectively integrating robust reasoning for Retrieval-Augmented Generation (RAG)
  arXiv  Detail & Related papers  (2025-03-27T17:44:18Z)
• Exploring the Necessity of Reasoning in LLM-based Agent Scenarios [74.35956310688164]
  We propose the LaRMA framework, encompassing nine tasks across Tool Usage, Plan Design, and Problem Solving.<n>Our findings address four research questions: LRMs surpass LLMs in reasoning-intensive tasks like Plan Design, leveraging iterative reflection for superior outcomes.<n>LRMs' enhanced reasoning incurs higher computational costs, prolonged processing, and behavioral challenges, including overthinking and fact-ignoring tendencies.
  arXiv  Detail & Related papers  (2025-03-14T04:34:31Z)
• Search-o1: Agentic Search-Enhanced Large Reasoning Models [24.239220558484373]
  Large reasoning models (LRMs) like OpenAI-o1 have demonstrated impressive long stepwise reasoning capabilities through large-scale reinforcement learning.<n>We introduce textbfSearch-o1, a framework that enhances LRMs with an agentic retrieval-augmented generation (RAG) mechanism and a Reason-in-Documents module.
  arXiv  Detail & Related papers  (2025-01-09T16:48:17Z)
• Enhancing LLM Reasoning with Reward-guided Tree Search [95.06503095273395]
  o1-like reasoning approach is challenging, and researchers have been making various attempts to advance this open area of research.<n>We present a preliminary exploration into enhancing the reasoning abilities of LLMs through reward-guided tree search algorithms.
  arXiv  Detail & Related papers  (2024-11-18T16:15:17Z)
• MR-Ben: A Meta-Reasoning Benchmark for Evaluating System-2 Thinking in LLMs [55.20845457594977]
  Large language models (LLMs) have shown increasing capability in problem-solving and decision-making.<n>We present a process-based benchmark MR-Ben that demands a meta-reasoning skill.<n>Our meta-reasoning paradigm is especially suited for system-2 slow thinking.
  arXiv  Detail & Related papers  (2024-06-20T03:50:23Z)
• Exploring Self-supervised Logic-enhanced Training for Large Language Models [59.227222647741094]
  In this paper, we make the first attempt to investigate the feasibility of incorporating logical knowledge through self-supervised post-training. We devise an auto-regressive objective variant of MERIt and integrate it with two LLM series, i.e., FLAN-T5 and LLaMA, with parameter size ranging from 3 billion to 13 billion. The results on two challenging logical reasoning benchmarks demonstrate the effectiveness of LogicLLM.
  arXiv  Detail & Related papers  (2023-05-23T06:13:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.