MindForge：通过无源程序合成教学小型语言模型全生命周期软件工程

摘要

编码智能体在修改现有代码库的软件工程任务上取得了显著进展，包括错误修复和功能实现。然而，从零开始构建完整程序仍然是一个重大挑战：即使在ProgramBench上评估的前沿模型，也完全解决了不到1%的任务。一个障碍是缺乏适用于这种从零开始场景的可扩展训练环境，该场景涵盖整个软件工程生命周期，因为现有的环境构建框架只专注于软件开发中的单个阶段。为填补这一空白，我们提出了MindForge，这是一个自动化管道，它将开源命令行程序转换为无源码环境，仅暴露一个编译好的参考可执行文件及其文档。利用MindForge，我们从与ProgramBench无关的代码仓库构建训练环境，并使用GLM-5.2作为教师智能体，策划了一套包含程序合成轨迹的高质量数据配方。在这些轨迹上对Qwen3.6-27B进行微调，使其在ProgramBench上的平均测试通过率从37.98%提升至49.51%，实现了与规模大得多的前沿模型相当的性能。此外，微调后的模型在所有七个未见过的软件工程基准测试上均持续优于基础模型，涵盖长时间仓库生成与翻译、错误修复、功能实现以及跨语言问题解决，在RepoZero-C2Rust上提升了31.00分，在DeepSWE上提升了14.16分，在NL2Repo-Bench上（有/无测试）提升了10.70/4.56分，在SWE-bench Verified上提升了5.04分，在SWE-bench Pro上提升了5.93分，在SWE-bench Multilingual上提升了5.22分，在FeatBench上提升了4.94分。

English

Coding agents have made substantial progress on software engineering tasks that modify existing codebases, including bug fixing and feature implementation. However, constructing a complete program from scratch remains a major challenge: even the frontier models evaluated on ProgramBench fully resolve fewer than 1% of tasks. One obstacle is the lack of scalable training environments for this from-scratch setting, spanning the whole software engineering life cycle, as existing environment-construction frameworks focus only on a single phase in software development. To address this gap, we introduce MindForge, an automated pipeline that converts open-source command-line programs into source-free environments that expose only a compiled reference executable and its documentation. Using MindForge, we construct training environments from repositories disjoint from those in ProgramBench, and curate a high-quality data recipe consisting of program synthesis trajectories using GLM-5.2 as the teacher agent. Fine-tuning Qwen3.6-27B on these trajectories increases its ProgramBench average test pass rate from 37.98% to 49.51%, achieving performance comparable to substantially larger frontier models. Moreover, the fine-tuned model consistently improves over the base model across all seven unseen software engineering benchmarks, spanning long-horizon repository generation and translation, bug fixing, feature implementation, and cross-language issue resolution, with absolute gains of 31.00 points on RepoZero-C2Rust, 14.16 on DeepSWE, 10.70/4.56 on NL2Repo-Bench (with/without tests), 5.04 on SWE-bench Verified, 5.93 on SWE-bench Pro, 5.22 on SWE-bench Multilingual, and 4.94 on FeatBench.