Metraipolis › archive › dc_078501801feb
Large Language Model-Guided Evolutionary Discovery of Native Neural Architectures for Spiking Sequence Modeling — arXiv:2609.40258
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.40258
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T15:14:14.560Z
- SHA-256 of the archived text
65548ea5b3e6e65ced60603b8977e259bf7c647077618107a5fe597d982e2cfe- Stable URL of this page
https://metraipolis.com/documento/dc_078501801feb
How to cite
Large Language Model-Guided Evolutionary Discovery of Native Neural Architectures for Spiking Sequence Modeling — arXiv:2609.40258 — arXiv (en), https://arxiv.org/abs/2609.40258 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_078501801feb (Metraipolis archive dc_078501801feb, sha256 65548ea5b3e6e65ced60603b8977e259bf7c647077618107a5fe597d982e2cfe)
BibTeX
@misc{dc078501801feb,
title = {Large Language Model-Guided Evolutionary Discovery of Native Neural Architectures for Spiking Sequence Modeling — arXiv:2609.40258},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.40258},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_078501801feb; sha256 65548ea5b3e6e65ced60603b8977e259bf7c647077618107a5fe597d982e2cfe},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.40258. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Spiking neural networks (SNNs) offer low-energy sequence modeling through sparse, event-driven computation. However, interactions among spike encoding, neuronal dynamics, and information propagation complicate architecture design. Existing SNN sequence models often adapt artificial neural network (ANN) architectures designed for real-valued activations, potentially underusing spike-based communication and temporal state updates, motivating automated discovery of native SNN architectures. Most evolutionary neural architecture search (ENAS) methods operate within predefined configuration spaces, limiting discovery to mechanisms expressible within those spaces. We introduce OpenArchEvo, which uses large language models (LLMs) to evolve executable architecture code in an open program space under spiking-projection constraints. In this space, code differences need not reflect architectural novelty, while direct performance evaluation requires costly training. We construct a three-view representation spanning code, design rationale, and a behavioral fingerprint to support novelty estimation and performance prediction. The search treats predicted performance and estimated novelty as two objectives, using surrogate predictions to select candidates for expensive training evaluations. With an estimated candidate-training cost of 132 V100 GPU-days, the search uncovers multiple native SNN architectures, exemplified by three designs featuring mechanisms such as spike-activity-dependent control of state updates and residual pathways. The discovered NeuroGate surpasses the ANN DeltaNet on WikiText-103, and the discovered architectures reduce estimated architecture-level arithmetic energy by up to 50.6x (LoopMem) relative to a common dense Transformer (ANN) baseline. All code and all discovered architectures will be made publicly available soon. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-01 in cs.NE). Categorie arXiv: Neural and Evolutionary Computing (cs.NE). Pagina del lavoro: https://arxiv.org/abs/2609.40258 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T14:47:35.110Z dalla pagina https://arxiv.org/catchup/cs.NE/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).