研究人员开发了一个名为ReLay的新框架，用于实现成本效益高的LLM驱动进化。该方法通过将预算从单个模型调用转移到进化种群来优化计算资源的分配。ReLay使用一个强盗调度器，让更便宜的模型在短块中探索多个轨迹，并由“Relay Gain”决定何时切换到更强大的模型。这种方法在各种基准测试中都显示出优越的性能，表明基于种群的预算分配对于有状态搜索更有效。 AI
影响 优化LLM驱动的进化过程的计算资源分配，可能降低复杂AI研究的成本。
排序理由 该集群描述了学术论文中发布的新框架和方法论。
在 arXiv cs.NE (Neural & Evolutionary) 阅读 →
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
arXiv:2608.05651v1 Announce Type: cross Abstract: Large language model (LLM)-driven evolution has shown promise for program search and algorithm discovery, but relying on strong models throughout long evolutionary runs is costly. A natural alternative is to combine cheap and stro…
Large language model (LLM)-driven evolution has shown promise for program search and algorithm discovery, but relying on strong models throughout long evolutionary runs is costly. A natural alternative is to combine cheap and strong models under a fixed inference budget. However,…
Large language model (LLM)-driven evolution has shown promise for program search and algorithm discovery, but relying on strong models throughout long evolutionary runs is costly. A natural alternative is to combine cheap and strong models under a fixed inference budget. However,…