Improving LLM Code Generation via Requirement-Aware Curriculum Reinforcement Learning

• URL: http://arxiv.org/abs/2605.00433v1
• Date: Fri, 01 May 2026 06:10:03 GMT
• Title: Improving LLM Code Generation via Requirement-Aware Curriculum Reinforcement Learning
• Abstract summary: We propose a novel requirement-aware curriculum reinforcement learning framework for enhancing large language models (LLMs)-based code generation.<n>We show that RECRL achieves an average Pass@1 improvement of 1.23%-5.62% over all state-of-the-art baselines.
• Score: 9.407248347872931
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Code generation, which aims to automatically generate source code from given programming requirements, has the potential to substantially improve software development efficiency. With the rapid advancement of large language models (LLMs), LLM-based code generation has attracted widespread attention from both academia and industry. However, as programming requirements become increasingly complex, existing LLMs still exhibit notable performance limitations. To address this challenge, recent studies have proposed training-based curriculum reinforcement learning (CRL) strategies to improve LLM code generation performance. Despite their effectiveness, existing CRL approaches suffer from several limitations, including misaligned requirement difficulty perception, the absence of requirement difficulty optimization, and suboptimal curriculum sampling strategies. In CRL-based code generation, programming requirements serve as the sole input to the model, making their quality and difficulty critical to training effectiveness. Motivated by insights from software requirements engineering, we propose RECRL, a novel requirement-aware curriculum reinforcement learning framework for enhancing LLM-based code generation. RECRL automatically perceives model-specific requirement difficulty, optimizes challenging requirements to improve training data utilization, and employs an adaptive curriculum sampling strategy to construct training batches with smoothly varying difficulty. Extensive experiments on five state-of-the-art LLMs across five widely-used code generation benchmarks by comparing with five state-of-the-art baselines, demonstrate the significant effectiveness of RECRL. For example, RECRL achieves an average Pass@1 improvement of 1.23%-5.62% over all state-of-the-art baselines.

Related papers

• GLM-5: from Vibe Coding to Agentic Engineering [222.46864802629477]
  We present GLM-5, a next-generation foundation model designed to transition the paradigm of vibe coding to agentic engineering.<n>Building upon the agentic, reasoning, and coding (ARC) capabilities of its predecessor, GLM-5 adopts DSA to significantly reduce training and inference costs while maintaining long-context fidelity.
  arXiv  Detail & Related papers  (2026-02-17T17:50:56Z)
• Aligning Requirement for Large Language Model's Code Generation [9.205909320363247]
  Specine is a novel specification alignment technique for large language models (LLMs) code generation.<n>Its key idea is to identify misaligned input specifications, lift LLM-perceived specifications, and align them to enhance the code generation performance of LLMs.<n>For example, Specine outperforms the most effective baseline, achieving an average improvement of 29.60% across all subjects in terms of Pass@1.
  arXiv  Detail & Related papers  (2025-09-01T09:56:13Z)
• ReST-RL: Achieving Accurate Code Reasoning of LLMs with Optimized Self-Training and Decoding [15.051729280454454]
  This paper introduces ReST-RL, a unified LLM RL paradigm.<n>It combines an improved GRPO algorithm with a meticulously designed test time decoding method assisted by a value model (VM)<n>We conduct extensive experiments on coding problems to verify the validity of the proposed RL paradigm.
  arXiv  Detail & Related papers  (2025-08-27T05:16:03Z)
• Large Language Model Unlearning for Source Code [65.42425213605114]
  PROD is a novel unlearning approach that enables LLMs to forget undesired code content while preserving their code generation capabilities.<n>Our evaluation demonstrates that PROD achieves superior balance between forget quality and model utility compared to existing unlearning approaches.
  arXiv  Detail & Related papers  (2025-06-20T16:27:59Z)
• Enhancing Code LLMs with Reinforcement Learning in Code Generation: A Survey [14.942504483776432]
  reinforcement learning (RL) has emerged as a pivotal technique for code generation and optimization.<n>This paper presents a systematic survey of the application of RL in code optimization and generation.
  arXiv  Detail & Related papers  (2024-12-29T06:15:41Z)
• Exploring Data-Efficient Adaptation of Large Language Models for Code Generation [64.5583894165813]
  We propose a novel adaptation approach named DEED, which stands for Data-Efficient adaptation with Error-Driven learning for code generation.<n> Experimental results show that, compared to other mainstream fine-tuning approaches, DEED achieves superior performance with few training data.
  arXiv  Detail & Related papers  (2024-02-29T16:09:02Z)
• StepCoder: Improve Code Generation with Reinforcement Learning from Compiler Feedback [58.20547418182074]
  We introduce StepCoder, a novel framework for code generation, consisting of two main components. CCCS addresses the exploration challenge by breaking the long sequences code generation task into a Curriculum of Code Completion Subtasks. FGO only optimize the model by masking the unexecuted code segments to provide Fine-Grained Optimization. Our method improves the ability to explore the output space and outperforms state-of-the-art approaches in corresponding benchmarks.
  arXiv  Detail & Related papers  (2024-02-02T13:14:31Z)
• PerfRL: A Small Language Model Framework for Efficient Code Optimization [14.18092813639534]
  In this paper, we introduce PerfRL, an innovative framework designed to tackle the problem of code optimization.<n>Our framework leverages the capabilities of small language models (SLMs) and reinforcement learning (RL)<n>Our approach achieves similar or better results compared to state-of-the-art models using shorter training times and smaller pre-trained models.
  arXiv  Detail & Related papers  (2023-12-09T19:50:23Z)
• LLM-Assisted Code Cleaning For Training Accurate Code Generators [53.087019724256606]
  We investigate data quality for code and find that making the code more structured and readable leads to improved code generation performance of the system. We build a novel data-cleaning pipeline that uses these principles to transform existing programs. We evaluate our approach on two challenging algorithmic code generation benchmarks and find that fine-tuning CodeLLaMa-7B improves the performance by up to 30% compared to fine-tuning on the original dataset.
  arXiv  Detail & Related papers  (2023-11-25T02:45:50Z)
• CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning [92.36705236706678]
  "CodeRL" is a new framework for program synthesis tasks through pretrained LMs and deep reinforcement learning. During inference, we introduce a new generation procedure with a critical sampling strategy. For the model backbones, we extended the encoder-decoder architecture of CodeT5 with enhanced learning objectives.
  arXiv  Detail & Related papers  (2022-07-05T02:42:15Z)

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.