{"ID":2827498,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.16406","arxiv_id":"2512.16406","title":"Hypernetworks That Evolve Themselves","abstract":"How can neural networks evolve themselves without relying on external optimizers? We propose Self-Referential Graph HyperNetworks, systems where the very machinery of variation and inheritance is embedded within the network. By uniting hypernetworks, stochastic parameter generation, and graph-based representations, Self-Referential GHNs mutate and evaluate themselves while adapting mutation rates as selectable traits. Through new reinforcement learning benchmarks with environmental shifts (CartPoleSwitch, LunarLander-Switch), Self-Referential GHNs show swift, reliable adaptation and emergent population dynamics. In the locomotion benchmark Ant-v5, they evolve coherent gaits, showing promising fine-tuning capabilities by autonomously decreasing variation in the population to concentrate around promising solutions. Our findings support the idea that evolvability itself can emerge from neural self-reference. Self-Referential GHNs reflect a step toward synthetic systems that more closely mirror biological evolution, offering tools for autonomous, open-ended learning agents.","short_abstract":"How can neural networks evolve themselves without relying on external optimizers? We propose Self-Referential Graph HyperNetworks, systems where the very machinery of variation and inheritance is embedded within the network. By uniting hypernetworks, stochastic parameter generation, and graph-based representations, Sel...","url_abs":"https://arxiv.org/abs/2512.16406","url_pdf":"https://arxiv.org/pdf/2512.16406v1","authors":"[\"Joachim Winther Pedersen\",\"Erwan Plantec\",\"Eleni Nisioti\",\"Marcello Barylli\",\"Milton Montero\",\"Kathrin Korte\",\"Sebastian Risi\"]","published":"2025-12-18T11:05:34Z","proceeding":"cs.NE","tasks":"[\"cs.NE\",\"cs.AI\"]","methods":"[\"Reinforcement Learning\"]","has_code":false}