**Φ-Bench: Can Large Language Models Engineer the Infrastructure That Powers The

**Φ-Bench: Can Large Language Models Engineer the Infrastructure That Powers Them?**

> Large language models (LLMs) have demonstrated remarkable capabilities in reasoning and code generation, raising the prospect that they could assist in developing and optimizing the very infrastructure that powers them. However, existing benchmarks mainly focus on isolated kernels, predefined operators, or pre-specified optimization targets, and therefore fail to evaluate the ability of LLMs to perform open-ended, lo...

**来源信息**
- **来源**：HuggingFace Daily Papers（社区热门论文）
- **分类**：论文
- **发布时间**：2026-09-10 08:00（北京时间）
- **原文**：[打开原文](https://huggingface.co/papers/2609.10226)