一篇新的研究论文介绍了一个名为 EvoX Genesis 的系统，该系统围绕持久化项目而非持久化代理来组织软件开发。这种方法支持长周期开发，通过使用 DeepSeek-V4 Flash 在 120 多个小时内以 44 美元的价格创建了一个基于 Rust 的 C 编译器来证明这一点。该编译器成功通过了广泛的测试套件。Genesis 还促进了 MESA 模块从 Fortran 到 Rust 的重新实现，实现了显著的速度提升。 AI
影响 这种方法可以实现更复杂、更自主的长期软件开发，有可能降低成本并提高效率。
排序理由 该集群包含一篇详细介绍新颖软件开发系统的研究论文。
在 arXiv cs.MA (Multiagent) 阅读 →
AI 生成摘要 · Google Gemini · 来自 4 个来源。 我们如何撰写摘要 →
完整方法见我们的编辑标准。
arXiv:2608.10450v1 Announce Type: cross Abstract: 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 intr…
Genesis organizes long-horizon software development around a persistent project rather than persistent agents, enabling multi-day compiler construction and numerical module reimplementation with low cost and high performance.
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 ins…
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 ins…