Metraipolis › archive › dc_0af94709d8bc
Consensus-gated Multi-Agent Neural Architecture Search for Seismic Fault Segmentation — arXiv:2608.13889
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.13889
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T04:02:15.213Z
- SHA-256 of the archived text
2fb986bc98f7b1ac5d5ced521354a73d88676dde9262f893b1795662a49a821e- Stable URL of this page
https://metraipolis.com/documento/dc_0af94709d8bc
How to cite
Consensus-gated Multi-Agent Neural Architecture Search for Seismic Fault Segmentation — arXiv:2608.13889 — arXiv (en), https://arxiv.org/abs/2608.13889 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0af94709d8bc (Metraipolis archive dc_0af94709d8bc, sha256 2fb986bc98f7b1ac5d5ced521354a73d88676dde9262f893b1795662a49a821e)
BibTeX
@misc{dc0af94709d8bc,
title = {Consensus-gated Multi-Agent Neural Architecture Search for Seismic Fault Segmentation — arXiv:2608.13889},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.13889},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0af94709d8bc; sha256 2fb986bc98f7b1ac5d5ced521354a73d88676dde9262f893b1795662a49a821e},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.13889. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Neural networks for seismic fault segmentation are often borrowed from computer vision and medical imaging domains where they train under relatively much larger labeled data resources. Optimizing their architecture under tight labeled data budgets as are common in geophysical applications is not a trivial problem. Manually designing data-optimal architectures is time-consuming while classical neural architecture search (NAS) is restricted to hand-crafted search spaces and large compute budgets. We present an agentic NAS system in which a panel of three large language models (Claude, GPT-5.1, and Gemini~2.5~Pro) debates each candidate architecture to unanimous consensus, authors the complete PyTorch implementation, cross-reviews it, and submits it to an automated validate-train-score loop with a hard 450K parameter budget, keep-or-revert lineage, and a memory of failed mechanisms. Operating on source code rather than a predefined operation menu, the search ran on a single consumer GPU and trained only eight candidates. It discovered \ours{}: a 425K-parameter encoder-decoder with a strip-pooling bottleneck, squeeze-and-excitation gating, an asymmetric one-conv decoder, and a feature-pyramid fusion neck. Trained under a protocol identical to all baselines on sections derived from the Thebe fault dataset, it attains the highest F1 (0.578) and IoU of all models tested while being the smallest, outperforming a published-capacity U-Net (31M parameters, F1 0.484), DeepLabV3-ResNet50 (39.6M, 0.516), an Attention U-Net(1.83M, 0.502). The search cost 101 LLM calls ($\sim$1.15M input / 0.39M output tokens) and roughly one GPU-day, making consensus-gated LLM panels a practical, low-cost route to domain-specific architecture discovery.
Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-17 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.13889 — 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 2026-10-19T03:57:57.764Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).