arXiv cs.CL· Chengyi Yang, Renxu Bao, Jue Hou, Zongpei Teng, Ziheng Wang, Yujie Lin, Chengsong Huang, Junnan Zhu, Delai Qiu, Yining Wang, Shengping Liu, Fei Long, Jinsong Su·· 6 天前AI 评分40
ProgramGym：为长周期程序复现智能体扩展训练环境
ProgramGym: Scaling Training Environments for Long-Horizon Program Reproduction Agents
AI 导读
研究团队提出 ProgramGym 框架，由 Program-Env 与 Program-Agent 组成，用于长周期程序复现智能体的可扩展训练环境。Program-Env 通过反馈驱动循环修复运行时沙箱构建与黑盒测试质量，构建出覆盖 C、C++、Go、Rust 的 1,648 个训练环境。
正文 · 原文
Authors:Chengyi Yang, Renxu Bao, Jue Hou, Zongpei Teng, Ziheng Wang, Yujie Lin, Chengsong Huang, Junnan Zhu, Delai Qiu, Yining Wang, Shengping Liu, Fei Long, Jinsong Su
Abstract:Coding agents are increasingly used to build programs from scratch as software engineers do rather than to resolve issues within a repository or to generate a repository from a given requirements document. However, scalable verifiable training environments that force agents to discover what is required and to decide how the system should be designed remain scarce. Moreover, existing agent workflows also cannot sustain long-horizon development in which the agent explores the reference program before implementation. To address these challenges, we introduce ProgramGym, a framework consisting of Program-Env and Program-Agent for scalable training environments of long-horizon program reproduction agents. Specifically, Program-Env constructs verifiable training environments from repositories through a feedback-driven loop that repairs runtime sandbox builds and the quality of black-box tests. Using this novel pipeline, we obtain 1,648 training environments spanning C, C++, Go, and Rust. Program-Agent combines a role-isolated workflow of analysis, implementation, and review with revision management for compilation checks and failure recovery. Experiments on ProgramBench show that both Program-Env and Program-Agent improve performance on program reproduction. Fine-tuning on trajectories with these constructed environments raises the performance of Qwen3.8-27B from 34.87% to 42.84%. Program-Agent further raises the base and SFT models to 55.71% and 56.25%, both exceeding some flagship models. We will release the ProgramGym to support further research on coding agents that build programs from scratch.
| Subjects: | Software Engineering (cs.SE); Artificial Intelligence (cs.AI); Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.13395 [cs.SE] |
| (or arXiv:2610.13395v1 [cs.SE] for this version) | |
| https://doi.org/10.48550/arXiv.2610.13395 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Chengyi Yang [view email]
[v1]
Fri, 9 Oct 2026 11:09:54 UTC (14,316 KB)
来源：arXiv cs.CL · arxiv.org