Multi-Behavioral Evolved Substrates Through Neuromodulation and Activation Selection

arXiv:2610.00148v1 Announce Type: cross Abstract: 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.

Abstract: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.

10 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: this https URL

Neural and Evolutionary Computing (cs.NE); Artificial Intelligence (cs.AI)

arXiv:2610.00148 [cs.NE]

(or arXiv:2610.00148v1 [cs.NE] for this version)

https://doi.org/10.48550/arXiv.2610.00148 arXiv-issued DOI via DataCite (pending registration)

ALIFE 2026: Proceedings of the 2026 Artificial Life Conference, MIT Press, 2026, p. 78

https://doi.org/10.1162/ISAL.a.968 DOI(s) linking to related resources

analiza aiqbench

Multi-Behavioral Evolved Substrates Through Neuromodulation and Activation Selection

Subiecte conexe