StoryCoder: Narrative Reformulation for Structured Reasoning in LLM Code Generation

2026-04-16

AI Summary

Large language models often struggle with code generation due to limited reasoning and planning capabilities, particularly when integrating fragmented problem constraints. This work proposes a narrative restructuring framework that, for the first time, incorporates human-like information organization into code generation. By guiding models through structured natural language narratives—including task overviews, explicit constraints, and example test cases—the approach enhances contextual understanding, improves algorithm selection accuracy, reduces implementation errors, and encourages modular code synthesis. Combining narrative restructuring, structured prompting, and reasoning guidance, the method achieves an average 18.7% improvement in zero-shot pass@10 across eleven mainstream models and demonstrates consistent effectiveness on multiple benchmarks, including HumanEval, LiveCodeBench, and CodeForces.

Technology Category

• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Machine Learning: Large Multimodal Models (LMMs)
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• Search and Retrieval-Augmented AI: Large language models for search
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

Effective code generation requires both model capability and a problem representation that carefully structures how models reason and plan. Existing approaches augment reasoning steps or inject specific structure into how models think, but leave scattered problem conditions unchanged. Inspired by the way humans organize fragmented information into coherent explanations, we propose StoryCoder, a narrative reformulation framework that transforms code generation questions into coherent natural language narratives, providing richer contextual structure than simple rephrasings. Each narrative consists of three components: a task overview, constraints, and example test cases, guided by the selected algorithm and genre. Experiments across 11 models on HumanEval, LiveCodeBench, and CodeForces demonstrate consistent improvements, with an average gain of 18.7% in zero-shot pass@10. Beyond accuracy, our analyses reveal that narrative reformulation guides models toward correct algorithmic strategies, reduces implementation errors, and induces a more modular code structure. The analyses further show that these benefits depend on narrative coherence and genre alignment, suggesting that structured problem representation is important for code generation regardless of model scale or architecture. Our code is available at https://github.com/gu-ni/StoryCoder.

Problem

• code generation
• structured reasoning
• problem representation
• narrative reformulation
• algorithmic planning

Innovation

• narrative reformulation
• structured reasoning
• code generation
• LLM prompting
• problem representation