# Aligning Requirement for Large Language Model's Code Generation

arXiv: https://arxiv.org/abs/2509.01313 · HTML: https://mlsanity.com/paper/2509.01313/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Sep 2025.

## Built on by (most cited first, 6 of 6)

- [REAgent: Requirement-Driven LLM Agents for Software Issue Resolution](https://mlsanity.com/paper/2604.06861/) (2026)
- [Advancing Language Models for Code-related Tasks](https://mlsanity.com/paper/2601.04526/) (2026)
- [Improving LLM Code Generation via Requirement-Aware Curriculum Reinforcement Learning](https://mlsanity.com/paper/2605.00433/) (2026)
- [WiseSpec: Requirements-Driven Agents for Code Generation](https://mlsanity.com/paper/2609.00568/) (2026)
- [CONTRA: Discovering and Qualifying Behavior-Changing Questions for Selective Clarification in LLM Code Generation](https://mlsanity.com/paper/2610.01769/) (2026)
- [Why Static Skill Inconsistencies Do Not Equate to Runtime Risks: A Behavioral Analysis of LLM Agent Execution](https://mlsanity.com/paper/2610.18927/) (2026)

## Abstract (arXiv)

Code generation refers to the automatic generation of source code based on a given programming specification, which has garnered significant attention particularly with the advancement of large language models (LLMs). However, due to the inherent complexity of real-world problems, the LLM-generated code often fails to fully align with the provided specification. While state-of-the-art agent-based techniques have been proposed to enhance LLM code generation, they overlook the critical issue of specification perception, resulting in persistent misalignment issues. Given that accurate perception of programming specifications serves as the foundation of the LLM-based code generation paradigm, ensuring specification alignment is particularly crucial. In this work, we draw on software requirements engineering to propose Specine, a novel specification alignment technique for LLM code generation. Its key idea is to identify misaligned input specifications, lift LLM-perceived specifications, and align them to enhance the code generation performance of LLMs. Our comprehensive experiments on four state-of-the-art LLMs across five challenging competitive benchmarks by comparing with ten state-of-the-art baselines, demonstrate the effectiveness of Specine. For example, Specine outperforms the most effective baseline, achieving an average improvement of 29.60% across all subjects in terms of Pass@1.