发表机构
The Hong Kong Polytechnic University（香港理工大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究提出 Genesis 框架，以持久递归世界替代持久智能体，成功构建 C 编译器、重实现 MESA 模块，实现长周期软件开发并获显著性能提升。
AI 中文摘要
复杂软件系统的开发周期远超单个编码智能体的生命周期。大多数智能体软件系统通过持久会话、记忆、管理器或共享上下文来保持连续性。我们提出 EvoX Genesis（以下简称 Genesis），它转而使软件项目保持持久，同时允许本地智能体具有有限生命周期。Genesis 将软件表示为持久递归世界：每个本地世界由已接受的版本和仓库路径定位，有限生命周期的智能体提出本地更改，递归委托将工作跨路径转移，且仅接受的结果会推进持久版本历史。我们在构建、延续和重新开发场景中评估该组织方式：从无编译器实现的仓库开始，Genesis 使用 DeepSeek V4 Flash 构建了一个基于 Rust 的 C 编译器，约 25 万行被追踪代码，运行时长超 120 小时，归档超 1000 个智能体 episodes，模型令牌费用仅 44 美元；该编译器通过了完整的 c-testsuite 及大部分 LLVM 和 Csmith 测试。在使用 GLM 5.2 生成的独立编译器世界中，智能体多次替换后开发仍能延续，同时保持完整测试性能。Genesis 还将 13 个 MESA 模块（超 10 万行 Fortran 代码）重新实现为近 9 万行 Rust 代码的 Rust 工作空间，在六个数值工作负载中实现了 1.55 至 6.87 倍的中位数加速。这些结果表明，长周期软件开发可围绕持久项目而非持久智能体来组织。
英文摘要
Complex software systems develop over timescales that exceed the lifespan of any individual coding agent. Most agentic software systems preserve continuity through persistent sessions, memories, managers or shared context. We introduce EvoX Genesis (hereafter, Genesis), which instead makes the software project persistent while allowing local agents to remain finite-lived. Genesis represents software as a persistent recursive world: each local world is situated by an accepted version and a repository path, finite-lived agents propose local changes, recursive delegation moves work across paths, and only accepted consequences advance the persistent version history. We evaluate this organization across formation, continuation and redevelopment. Starting from a repository with no compiler implementation, Genesis used DeepSeek V4 Flash to build a Rust-based C compiler with about 250k tracked lines; the run lasted over 120 hours, archived over 1,000 agent episodes and incurred only US\$44 in model-token charges. The compiler passed the complete c-testsuite and most LLVM and Csmith tests. In a separate compiler world generated with GLM 5.2, development continued after repeated agent replacement while retaining full test performance. Genesis also reimplemented 13 MESA modules with over 100k Fortran lines as a Rust workspace with nearly 90k Rust lines; across six numerical workloads, it achieved median speedups of 1.55--6.87x. These results show that long-horizon software development can be organized around a persistent project rather than a persistent agent. Project Website: https://genesis.evox.group/
