发表机构
Osaka Metropolitan University（大阪公立大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
T-GADE通过热力学遗传算法与LLM遗传算子演化结构化工件，在在线装箱任务中显著降低训练超额，并达到与EoH相当的迁移性能。
AI 中文摘要
将进化计算与大型语言模型（LLM）相结合，需要控制种群多样性以及生成能力。在LLM的输出中，那些具有显式结构的输出，例如描述与代码配对，被称为结构化工件；我们简称为工件。我们提出了T-GADE，它通过基于LLM的遗传算子和工件级多样性评估来扩展热力学遗传算法，从而演化这些工件。一个共同的自由能目标支持世代更新和稳态更新，其中费米型占据排除重复基因型，而玻色型占据允许重复基因型。我们建立了精确的单成员移除条件，并给出了恢复启发式演化（EoH）零温生存规则的条件。在EoH论文研究的在线装箱任务中，超额度量是相对于体积下界的相对箱数开销。训练超额使用搜索实例；迁移超额使用具有另一种箱容量的实例。在$T=0.003$下，世代玻色型T-GADE在每种配置20次运行中，将中位训练超额从1.152%降低至0.815%，相对降低约29%（双边Mann-Whitney $p=0.042$，Cliff's $\delta=0.378$）。在其两个排名最高的最终候选中进行验证选择，达到了与EoH相同的中位迁移超额，即0.496%。这些结果证明了热力学选择和基于验证的保留工件使用的有效性。
英文摘要
Integrating evolutionary computation and large language models (LLMs) requires control of population diversity as well as generative capability. Among LLM outputs, those with explicit structure, such as a description paired with code, are structured artifacts; we use artifact for short. We propose T-GADE, which evolves these artifacts by extending thermodynamical genetic algorithms through LLM-based genetic operators and artifact-level diversity evaluation. A common free-energy objective supports generational and steady-state updates, with Fermi-type occupancy excluding repeated genotypes and Bose-type occupancy permitting them. We establish exact one-member removal and conditions for recovering the zero-temperature survival rule of Evolution of Heuristics (EoH). On the online bin-packing task studied in the EoH paper, excess measures relative bin-count overhead above a volume lower bound. Training excess uses search instances; transfer excess uses instances with another bin capacity. Generational Bose-type T-GADE at $T=0.003$ reduced median training excess by approximately 29%, from 1.152% to 0.815%, over 20 runs per configuration (two-sided Mann-Whitney $p=0.042$, Cliff's $δ=0.378$). Validation selection among its two highest-ranked final candidates reached the same median transfer excess as EoH, 0.496%. These results demonstrate the utility of thermodynamical selection and validation-based use of retained artifacts.
