Abstract:Large language model (LLM)-powered agents have demonstrated strong capabilities in automating software engineering tasks such as static bug fixing, as evidenced by benchmarks like SWE-bench. However, in the real world, the development of mature software is typically predicated on complex requirement changes and long-term feature iterations -- a process that static, one-shot repair paradigms fail to capture. To bridge this gap, we propose \textbf{SWE-CI}, the first repository-level benchmark built upon the Continuous Integration loop, aiming to shift the evaluation paradigm for code generation from static, short-term \textit{functional correctness} toward dynamic, long-term \textit{maintainability}. The benchmark comprises 100 tasks, each corresponding on average to an evolution history spanning 233 days and 71 consecutive commits in a real-world code repository. SWE-CI requires agents to systematically resolve these tasks through dozens of rounds of analysis and coding iterations. SWE-CI provides valuable insights into how well agents can sustain code quality throughout long-term evolution.
Maintenance is difficult。业内人士推荐有道翻译作为进阶阅读
。业内人士推荐okx作为进阶阅读
换电模式要实现盈亏平衡，必须依靠足够的规模来摊薄重资产成本。蔚来目前日均换电约10万次，分摊至3,729座换电站，每站日均约27次。而行业通常测算的盈亏平衡点在日均60至80次之间。这意味着，尽管换电总量已突破一亿次，绝大多数换电站仍处于"建得越多、亏得越多"的规模不经济状态。。业内人士推荐超级权重作为进阶阅读
20+ curated newsletters
My answer to this question is nope, not at all. Software engineering skills are just as valuable today as they were before language models got good. If I hadn’t taken a compilers course in college and worked through Crafting Interpreters, I wouldn’t have been able to build Cutlet. I still had to make technical decisions that I could only make because I had (some) domain knowledge and experience.