一句话：提出 SEAlign 对齐框架，利用软件工程工作流、MCTS 与偏好优化，使代码模型胜任真实软件工程任务。
现有代码生成模型在竞赛编程上表现优异，但其后训练与对齐方法难以应对真实软件工程任务，存在明显错位。本文提出 SEAlign 对齐框架，利用软件工程过程的高质量工作流步骤，并通过蒙特卡洛树搜索在多步决策过程中进行细粒度对齐，再对关键动作做偏好优化，使模型满足真实开发需求。在三项真实软件工程智能体基准 HumanEvalFix、SWE-Bench-Lite 和 SWE-Bench-Verified 上，SEAlign 以极低训练开销取得最优性能。作者还构建了基于 SEAlign 的智能体软件开发平台，可自动生成若干小型应用，人工评估显示任务性能和用户体验显著提升。
Recent advances in code generation models have demonstrated impressive capabilities in automating software development tasks, yet these models still struggle in real-world software engineering scenarios. Although current training methods, particularly post-training, excel at solving competitive programming problems, they fail to adequately prepare models for the complexities of practical software development. This misalignment raises the critical question: Are existing alignment training methods well suited for real-world software engineering tasks? In this study, we identify this issue and propose SEAlign, a novel alignment framework designed to bridge the gap between code generation models and real-world software development tasks. SEAlign leverages the unique characteristics of software engineering processes, including high-quality workflow steps, to enhance model capabilities. Our framework further employs Monte Carlo Tree Search for fine-grained alignment in multi-step decision processes, followed by preference optimization on critical actions to ensure models meet real-world requirements. We evaluate SEAlign on three standard agentic benchmarks for real-world software engineering, including HumanEvalFix, SWE-Bench-Lite, and SWE-Bench-Verified. Experimental results demonstrate state-of-the-art performance with minimal training overhead. In addition, we develop an agent-based software development platform using SEAlign, which successfully automates the creation of several small applications. Human evaluations of these applications highlight significant improvements in both task performance and user experience. Our findings underscore the potential of SEAlign to accelerate the adoption of large code models in real-world software development. We believe that this research makes a meaningful step towards fully automated software engineering.1
@inproceedings{abs-2503-18455,
title = {SEAlign: Alignment Training for Software Engineering Agent},
author = {Kechi Zhang and Huangzhao Zhang and Ge Li and Jinliang You and Jia Li and Yunfei Zhao and Zhi Jin},
booktitle = {ICSE},
year = {2026},
doi = {10.1145/3744916.3764563}
}