1
Runtime-Structured Task Decomposition for Agentic Coding Systems
LLM驱动的编码系统常因单体提示而脆弱难调试，这篇论文提出运行时结构化任务分解，让失败诊断与重试更高效。
arXiv:2605.15425v1 Announce Type: cross Abstract: Agentic coding systems increasingly use large language models (LLMs) for software engineering tasks …