想低成本搞大型软件项目？EvoX Genesis 用 44 美元让 AI 写了 25 万行编译器，换人也不掉链子，值得看看。
EvoX Genesis 框架将软件项目设为持久递归世界，本地智能体保持有限寿命，通过递归委派推进版本历史。基于 DeepSeek V4 Flash，Genesis 在 120 小时内构建了约 25 万行 Rust 的 C 编译器，花费仅 44 美元，通过完整 c-testsuite 及多数 LLVM 和 Csmith 测试。在 GLM 5.2 生成的编译器世界中，多次替换智能体后开发仍保持全部测试性能。Genesis 还将 13 个 MESA 模块（超 10 万行 Fortran）重写为约 9 万行 Rust，六个数值工作负载中位数加速 1.55 至 6.87 倍。结果表明，长期软件开发可围绕持久项目而非持久智能体组织。
Persistent Recursive Worlds Enable Autonomous Software Evolution
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.