发表机构
University of Neuchâtel; University College Dublin（纳沙泰尔大学; 都柏林大学学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究通过CPPN间接编码基板，结合神经调节与每任务激活函数选择，克服了单调激活函数在奇偶校验任务上的75%演化搜索上限，实现多行为基板100%的5任务同时成功率，表明计算原语应为可演化特征。
AI 中文摘要
开放式人工生命系统必须从单一演化基因型中获取多种多样的能力。生物大脑将神经调节（在不改变连接的情况下重构电路）与匹配特定计算角色的多种神经元类型相结合。人工演化能否在间接编码的基板中实现类似的效果？我们使用通过CPPN演化的间接编码基板，通过超过10,000次实验表明，仅靠神经调节是不够的：在演化搜索下，单调激活函数在奇偶校验任务上施加了75%的上限，无论容量、拓扑或种群规模如何，该上限都持续存在。这是一个演化搜索障碍，而非表示限制，因为Adam梯度下降在相同架构上达到了100%的成功率。我们将神经调节与每任务激活函数选择相结合，将振荡原语匹配到奇偶校验任务，将单调函数匹配到阈值任务，从而产生多行为演化基板。结果是：在所有30个种子中，同时完成5项任务的成功率达到100%（中位数为14代）。这一结果在振荡激活类别中具有普遍性：所有四种函数均达到100%（每种30个种子）。单独使用任一机制都不够。该障碍扩展到更高元数和不对称任务，而多层深度提供了替代路径。对于开放式演化，计算原语本身应成为可演化的特征。在推理时，一个演化基因型表达多种行为。
英文摘要
Open-ended artificial life systems must acquire diverse competencies from a single evolving genotype. Biological brains combine neuromodulation, which reconfigures circuits without changing connections, with diverse neuron types matched to specific computational roles. Can artificial evolution achieve something analogous in indirectly encoded substrates? Using indirectly encoded substrates evolved via CPPNs, we show through more than 10,000 experiments that neuromodulation alone is insufficient: under evolutionary search, monotonic activation functions impose a 75% ceiling on parity tasks that persists regardless of capacity, topology, or population size. This is an evolutionary search barrier, not a representational limit, since Adam gradient descent achieves 100% on the identical architecture. We combine neuromodulation with per-task activation function selection, matching oscillatory primitives to parity tasks and monotonic to threshold tasks, producing multi-behavioral evolved substrates. The result: 100% simultaneous 5-task success across all 30 seeds (median 14 generations). This generalizes across the oscillatory activation class: all four functions reach 100% (30 seeds each). Neither mechanism suffices alone. The barrier extends to higher-arity and asymmetric tasks, while multi-layer depth provides an alternative path. For open-ended evolution, the computational primitive should itself be an evolvable trait. At inference, one evolved genotype expresses many behaviors.
Comments10 pages, 3 figures, 3 tables. Published version of the paper presented at ALIFE 2026: Proceedings of the 2026 Artificial Life Conference (MIT Press). Code and data: https://github.com/RomainClaret/emr-hyperneat
Journal refALIFE 2026: Proceedings of the 2026 Artificial Life Conference, MIT Press, 2026, p. 78
