正在加载原动态…在 X 上查看 ↗
Giving an LLM maze-solving judgment only at junctions while code holds the DFS stack and visited set solved a 14×14 braided maze in 22 calls and 56 steps (2.2× optimal), versus 60 per-step calls that just paced a 7-cell corridor at 96% confidence.
原始动态
正在加载原动态…在 X 上查看 ↗
jev
输入关键词以查找应用案例。