From Reasoning to Code: GRPO Optimization for Underrepresented Languages

• URL: http://arxiv.org/abs/2506.11027v2
• Date: Mon, 16 Jun 2025 09:41:16 GMT
• Title: From Reasoning to Code: GRPO Optimization for Underrepresented Languages
• Authors: Federico Pennino, Bianca Raimondi, Massimo Rondelli, Andrea Gurioli, Maurizio Gabbrielli,
• Abstract summary: This paper introduces a generalizable approach that uses small-scale code versions of the Qwen 2.5 model combined with Group Relative Policy Optimization.<n>It produces logically consistent and syntactically accurate code by directly integrating reasoning-driven feedback into the reinforcement learning loop.
• Score: 0.7864304771129751
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Generating accurate and executable code using large language models (LLMs) is challenging for languages with limited public training data compared to popular languages such as Python. This paper introduces a generalizable approach that uses small-scale code versions of the Qwen 2.5 model combined with Group Relative Policy Optimization (GRPO) to enable effective code generation through explicit reasoning steps, which is particularly beneficial for languages with smaller source code databases. Using Prolog as a representative use case -- given its limited online presence -- the initial model faced challenges in generating executable code. After some training steps, the model successfully produces logically consistent and syntactically accurate code by directly integrating reasoning-driven feedback into the reinforcement learning loop. Experimental evaluations using mathematical logic problem benchmarks illustrate significant improvements in reasoning quality, code accuracy, and logical correctness, underscoring the potential of this approach to benefit a wide range of programming languages lacking extensive training resources.

Related papers

• IFEvalCode: Controlled Code Generation [69.28317223249358]
  The paper introduces forward and backward constraints generation to improve the instruction-following capabilities of Code LLMs.<n>The authors present IFEvalCode, a multilingual benchmark comprising 1.6K test samples across seven programming languages.
  arXiv  Detail & Related papers  (2025-07-30T08:08:48Z)
• Re:Form -- Reducing Human Priors in Scalable Formal Software Verification with RL in LLMs: A Preliminary Study on Dafny [68.00108157244952]
  Large Language Models (LLMs) trained with Reinforcement Learning (RL) face a significant challenge: their verification processes are neither reliable nor scalable.<n>A promising yet largely uncharted alternative is formal language-based reasoning.<n>Grounding LLMs in rigorous formal systems where generative models operate in formal language spaces (e.g., Dafny) enables the automatic and mathematically provable verification of their reasoning processes and outcomes.
  arXiv  Detail & Related papers  (2025-07-22T08:13:01Z)
• Is Compression Really Linear with Code Intelligence? [60.123628177110206]
  textitFormat Annealing is a lightweight, transparent training methodology designed to assess the intrinsic capabilities of pre-trained models equitably.<n>Our empirical results reveal a fundamental logarithmic relationship between measured code intelligence and bits-per-character (BPC)<n>Our work provides a more nuanced understanding of compression's role in developing code intelligence and contributes a robust evaluation framework in the code domain.
  arXiv  Detail & Related papers  (2025-05-16T16:59:14Z)
• Program Semantic Inequivalence Game with Large Language Models [10.358176296850639]
  Large Language Models (LLMs) can achieve strong performance on everyday coding tasks, but they can fail on complex tasks that require non-trivial reasoning about program semantics.<n>In this work, we explore a method to synthetically generate code reasoning training data based on a semantic inequivalence game SInQ.<n>We prove that this setup enables theoretically unlimited improvement through self-play in the limit of infinite computational resources.
  arXiv  Detail & Related papers  (2025-05-02T20:03:35Z)
• Type-Constrained Code Generation with Language Models [51.03439021895432]
  We introduce a type-constrained decoding approach that leverages type systems to guide code generation.<n>For this purpose, we develop novel prefix automata and a search over inhabitable types, forming a sound approach to enforce well-typedness on LLM-generated code.<n>Our approach reduces compilation errors by more than half and significantly increases functional correctness in code synthesis, translation, and repair tasks.
  arXiv  Detail & Related papers  (2025-04-12T15:03:00Z)
• On Explaining (Large) Language Models For Code Using Global Code-Based Explanations [45.126233498200534]
  Language Models for Code (LLM4Code) have significantly changed the landscape of software engineering (SE)<n>We introduce code rationales (Code$Q$), a technique with rigorous mathematical underpinning, to identify subsets of tokens that can explain individual code predictions.<n>Our evaluation demonstrates that Code$Q$ is a powerful interpretability method to explain how (less) meaningful input concepts (i.e., natural language particle at') highly impact output generation.
  arXiv  Detail & Related papers  (2025-03-21T01:00:45Z)
• CodeDPO: Aligning Code Models with Self Generated and Verified Source Code [52.70310361822519]
  We propose CodeDPO, a framework that integrates preference learning into code generation to improve two key code preference factors: code correctness and efficiency.<n>CodeDPO employs a novel dataset construction method, utilizing a self-generation-and-validation mechanism that simultaneously generates and evaluates code and test cases.
  arXiv  Detail & Related papers  (2024-10-08T01:36:15Z)
• An Effective Approach to Embedding Source Code by Combining Large Language and Sentence Embedding Models [6.976968804436321]
  This paper proposes a novel approach to embedding source code by combining large language and sentence embedding models.<n>To evaluate the performance of our proposed approach, we conducted a series of experiments on three datasets with different programming languages.
  arXiv  Detail & Related papers  (2024-09-23T01:03:15Z)
• Unlocking Reasoning Potential in Large Langauge Models by Scaling Code-form Planning [94.76546523689113]
  We introduce CodePlan, a framework that generates and follows textcode-form plans -- pseudocode that outlines high-level, structured reasoning processes. CodePlan effectively captures the rich semantics and control flows inherent to sophisticated reasoning tasks. It achieves a 25.1% relative improvement compared with directly generating responses.
  arXiv  Detail & Related papers  (2024-09-19T04:13:58Z)
• Large Language Model for Verilog Generation with Code-Structure-Guided Reinforcement Learning [29.135207235743795]
  This paper introduces VeriSeek, an LLM enhanced by reinforcement learning to achieve high Verilog code generation performance.<n>Our reinforcement learning approach employs code structure information as feedback signals to refine the pre-trained model.<n>Experiments show that VeriSeek outperforms state-of-the-art methods across multiple benchmarks.
  arXiv  Detail & Related papers  (2024-07-21T11:25:21Z)
• CodeGRAG: Bridging the Gap between Natural Language and Programming Language via Graphical Retrieval Augmented Generation [58.84212778960507]
  CodeGRAG builds the graphical view of code blocks based on the control flow and data flow of them to better interpret the programming domain knowledge.<n>CodeGRAG significantly improves the code generation ability of LLMs and can even offer performance gain for cross-lingual code generation.
  arXiv  Detail & Related papers  (2024-05-03T02:48:55Z)

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.