1
How Generation Architecture Shapes Code Complexity in Multi-Agent LLM Systems: A Paired Study on HumanEval
一项研究揭示多智能体LLM架构不仅影响代码正确性，还会改变代码的结构复杂度。
arXiv:2606.00308v1 Announce Type: cross Abstract: Large-language-model code generation has shifted from single-shot prompting to multi-agent orchestra…