MEnvAgent：面向可验证软件工程的可扩展多语言环境构建平台

MEnvAgent: Scalable Polyglot Environment Construction for Verifiable Software Engineering

January 30, 2026

作者: Chuanzhe Guo, Jingjing Wu, Sijun He, Yang Chen, Zhaoqi Kuang, Shilong Fan, Bingjin Chen, Siqi Bao, Jing Liu, Hua Wu, Qingfu Zhu, Wanxiang Che, Haifeng Wang

cs.AI

摘要

针对软件工程领域大语言模型智能体发展的可验证数据集稀缺问题，我们提出MEnvAgent——一种支持多语言的自动化环境构建框架。该框架通过规划-执行-验证的多智能体架构自主解决环境构建故障，并创新性地引入环境复用机制，通过增量式修补历史环境显著降低计算开销。基于涵盖10种编程语言的千级任务基准测试MEnvBench的实验表明，MEnvAgent在失败转通过率上较基线提升8.6%，同时时间成本降低43%。基于此框架构建的MEnvData-SWE成为迄今规模最大的开源多语言可验证Docker环境数据集，其配套的解决方案轨迹能持续提升各类模型在软件工程任务上的表现。相关代码、基准测试及数据集已开源：https://github.com/ernie-research/MEnvAgent。

English

The evolution of Large Language Model (LLM) agents for software engineering (SWE) is constrained by the scarcity of verifiable datasets, a bottleneck stemming from the complexity of constructing executable environments across diverse languages. To address this, we introduce MEnvAgent, a Multi-language framework for automated Environment construction that facilitates scalable generation of verifiable task instances. MEnvAgent employs a multi-agent Planning-Execution-Verification architecture to autonomously resolve construction failures and integrates a novel Environment Reuse Mechanism that reduces computational overhead by incrementally patching historical environments. Evaluations on MEnvBench, a new benchmark comprising 1,000 tasks across 10 languages, demonstrate that MEnvAgent outperforms baselines, improving Fail-to-Pass (F2P) rates by 8.6% while reducing time costs by 43%. Additionally, we demonstrate the utility of MEnvAgent by constructing MEnvData-SWE, the largest open-source polyglot dataset of realistic verifiable Docker environments to date, alongside solution trajectories that enable consistent performance gains on SWE tasks across a wide range of models. Our code, benchmark, and dataset are available at https://github.com/ernie-research/MEnvAgent.