Neural Architecture Search

Also known as NAS

Neural Architecture Search (NAS) studies how to choose or generate a neural network’s structure so it performs well on a task without relying entirely on manual design. Common approaches include differentiable search such as DARTS, evolutionary and reinforcement-learning methods, weight-sharing supernets, and surrogate or zero-cost predictors that estimate candidate quality cheaply. Increasingly, search also accounts for latency, memory, energy, quantization, and deployment conditions, using hardware measurements or learned cost models alongside accuracy. The central tension is how to make search economical while ensuring that cheap proxies and benchmark results reliably predict performance after full training and on real devices.

Latest papers

130 papers21 papers in the last four weeks, up 75% on the four weeks before. 0.1% of all new papers.

TRON: Transferring Naturally Evolved Network Architectures into Neuroevolution
Oct 26, 2026Konstantinos Zacharopoulos, Alexandra Bekou, Jose M Serradell +4Neural Architecture Search Neuroevolution
Technical University of Crete, ECE Department, Chania, 732 00, Greece · R.C. ATHENA, Industrial Systems Institute, Patras, 265 04, Greece · IBE, Institute of Evolutionary Biology (CSIC-Universitat Pompeu Fabra), Barcelona, 08003, Spain +1
Searching with Sparse Histories: Cross-Task Architecture Search from Incomplete Search Logs and Zero-Cost Proxies
Oct 23, 2026Yuefeng Xu, Jun YuNeural Architecture Performance Prediction Neural Architecture Search
Graduate School of Science and Technology, Niigata University, Niigata, Japan · Institute of Science and Technology, Niigata University, Niigata, Japan
QuaNAS: Uncertainty-Aware Reuse of Earlier Searches for Query-Efficient Neural Architecture Search
Oct 22, 2026Brama Seta Putra Satria, Dwi Sunaryono, Misbakhul Munir Irfan Subakti +2Neural Architecture Search Uncertainty-Aware Exploration
Department of Informatics, Institut Teknologi Sepuluh Nopember, Surabaya, Indonesia · Department of Information Technology, Institut Teknologi Sepuluh Nopember, Surabaya, Indonesia · Department of Electrical Engineering, Institut Teknologi Sepuluh Nopember, Surabaya, Indonesia
Neural Spectral Capacity with Residual Context for Heterogeneous Resource Allocation within Transformers
Oct 22, 2026Chenyu Zhu, Ruoyu Zhao, Zhichao LuNeural Architecture Performance Prediction Neural Architecture Search
Department of Computer Science, City University of Hong Kong
Building AI Research Teams for Autonomous Discovery of Linear Attention Architectures
Oct 20, 2026Yujian Liu, Li An, Zelin He +5Autonomous Scientific Discovery Multi-Agent Collaboration
UC Santa Barbara · Pennsylvania State University · LinkedIn
DTA-GT: Direction- and Topology-Aware Graph Transformer for Neural Network Representation Learning
Oct 12, 2026Yuxiang Zeng, Kun Xie, Yang Wang +5Neural Architecture Performance Prediction Graph Transformer
Hunan University · Hunan University of Science and Technology · Chinese Academy of Sciences +1
FENAS: A Few-Shot Meta-Ensembling Framework for Efficient Neural Architecture Search with Synergized Zero-Cost Proxies
Oct 11, 2026Yifeng Mao, Yuze Feng, Yutong Shen +2Neural Architecture Search
Beijing University of Technology, Beijing, China
GeoBridge: Evolving Transferable Decoder Topologies for Geometric Vision
Oct 11, 2026Rui Wang, Haoyu Zhang, Ran ChengNeural Architecture Search Depth Estimation
School of Information Science and Technology, Hangzhou Normal University, Hangzhou, P.R. China · Department of Data Science and Artificial Intelligence, The Hong Kong Polytechnic University, Hong Kong SAR, China
Efficient Audio-Visual Speech Enhancement via Reinforcement Learning-Based Neural Architecture Search
Oct 8, 2026Khubaib Ahmed, Ahsan Adeel, Nasir Saleem +3Speech Enhancement Neural Architecture Search
University of Stirling, UK · Edinburgh Napier University, UK · University of Technology and Applied Sciences, Oman
Evolutionary Architecture Search for Chlorophyll- $a$ Prediction in Lakes using Sentinel-2
Oct 7, 2026Kursat Komurcu, Linas PetkeviciusNeural Architecture Search Remote Sensing
Vilnius University, Institute of Computer Science, Artificial Intelligence Methods Lab · IRISA, Universite Bretagne Sud · European Commission Joint Research Center
Evolve on the Host, Predict on the Edge: Deploying Online Neuroevolutionary Architecture Search for Cross-sectional Stock Return Prediction
Oct 7, 2026Jonathan Chang, Zimeng LyuStock Price Forecasting Time Series Forecasting
Union County Magnet High School · Department of Computer Science and Technology, Kean University
Node-level Graph Neural Architecture Search Framework
Oct 7, 2026Lintao Yanga, Sirui Lia, Yaqing Wang +4Graph Neural Networks Neural Architecture Search
College of Information Science and Engineering, Ningbo University, Ningbo, 315211, China · Department of Computer Science and Technology, University of Cambridge, Cambridge, CB3 0FD, UK · School of Artificial Intelligence, Jilin University, Changchun, 130015, China
Forecast Accuracy Is Not Trading Profit: Evolving Small Recurrent Networks for Stock Return Prediction
Oct 6, 2026Jonathan Chang, Zimeng LyuTime Series Forecasting Recurrent Neural Networks
Union County Magnet High School Scotch Plains, New Jersey, USA · Kean University Union, New Jersey, USA
Bayesian Optimization in Sequence-to-Architecture Latent Space for Zero-Shot NAS
Oct 5, 2026Ondrej Tybl, Lukas NeumannBayesian Optimization Neural Architecture Search
Department of Cybernetics FEE Czech Technical University
Active-DiNTS: Active Differentiable Network Topology Search
Oct 3, 2026Gean Trindade Pereira, Thierry Urruty, Muriel Visani +1Neural Architecture Search 3D Medical Image Segmentation
Institute of Mathematics and Computer Sciences (ICMC) University of São Paulo São Carlos, 13560-970, São Paulo, Brazil · XLIM, Université de Poitiers Université de Limoges, CNRS Poitiers, 86000, Vienne, France · Laboratoire Informatique, Image et Interaction (L3i) La Rochelle Université La Rochelle, 17042, Charente-Maritime, France
EvoCast: Reliable Autonomous Research Agents for Iterative Forecasting Architecture Evolution
Oct 3, 2026Kaipeng Xu, Xianli Yan, Yan Wang +2Autonomous Research Agents Automated Machine Learning
School of Automation and Intelligent Science, Jiangnan University, Wuxi 214122, China · School of Automation, Southeast University, Nanjing 210096, China
Coverage You Can Steer: Online Conformal Calibration for RL-Driven Hardware-Aware NAS
Oct 2, 2026Pedro Brandimarte, Nerea Aranjuelo, Marcos Nieto +1Neural Architecture Search Conformal Prediction
Vicomtech Foundation, Basque Research and Technology Alliance (BRTA) Donostia-San Sebasti´an, Spain
LESS: Lightweight Evolutionary Supernet Search in Minutes
Oct 1, 2026Aviral Gandhi, Jinglue Xu, Jialong Li +1Evolutionary Optimization Covariance Matrix Adaptation Evolution Strategy
The University of Tokyo · Sakana AI · Waseda University
Prediction-powered Neural Architecture Search
Oct 1, 2026Pascal Janetzky, Yuxin Wang, Michael Klar +1Neural Architecture Search Prediction-Powered Inference
Bosch Center for Artificial Intelligence · LMU Munich Munich Center for Machine Learning(MCML)
CAGE-NAS: Certified Functional Descent for Efficient Model Growth
Oct 1, 2026Santiago Florido Gomez, Stéphane RivaudGradient Descent Neural Network Optimization
Institut Polytechnique de Paris Paris, France · Inria Saclay, TAU Team Paris, France
Large Language Model-Guided Evolutionary Discovery of Native Neural Architectures for Spiking Sequence Modeling
Sep 30, 2026Ruoyu Zhao, Jiaqi Wu, Chenyu Zhu +1Large Language Model-Guided NAS Spiking Neural Networks
Department of Computer Science, City University of Hong Kong
AutoBCI: Forecast-Guided Agentic Neural Architecture Discovery for EEG-Based Brain--Computer Interfaces
Sep 28, 2026Muyun Jiang, Yi Ding, Wei Zhang +9Brain-Computer Interfaces Large Language Model-Guided NAS
Nanyang Technological University, Singapore · The University of Hong Kong, Hong Kong, China · Southeast University, China
ThinkNet: Evolutionary Deep Ensembles for Efficient Motor-Imagery EEG Classification
Sep 27, 2026Abdul Basit, Saim Rehman, Muhammad ShafiqueCross-Subject EEG Decoding MI Classification
eBRAIN Lab, Division of Engineering New York University (NYU) Abu Dhabi, Abu Dhabi, UAE
AutoHGNN: Robust and Efficient Neural Architecture Search for Hypergraph Neural Networks
Sep 27, 2026Sirui Li, Pietro Liò b, Xinsheng Li +2Hypergraph Neural Networks Neural Architecture Search
Faculty of Electrical Engineering and Computer Science, Ningbo University, Ningbo, 315211, Zhejiang, China · Department of Computer Science and Technology, University of Cambridge, Cambridge, CB2 1TN, Cambridgeshire, United Kingdom
Rank-Reliable Teacher-Guided Fitness Approximation for Expensive Evolutionary Optimization: A TinyML Architecture Search Study
Sep 24, 2026Soumen Garai, Suman SamuiNeural Architecture Search Multi-Fidelity Optimization
Department of Electronics and Communication Engineering, National Institute of Technology Durgapur, West Bengal 713209, India
EvoTreeNAD: Genealogy-Guided Evolution for LLM-Driven Neural Architecture Discovery
Sep 24, 2026Lishan Yu, Derek Jiu, Qizhen Lan +1Large Language Model-Guided NAS Evolutionary Optimization
Department of Health Data Science and AI McWilliams School of Biomedical Informatics University of Texas Health Science Center at Houston
NGN: Learning Neural Network Size as a Differentiable Count
Sep 23, 2026Lixing LiDynamic Neural Networks Neural Architecture Search
Cornell University Ithaca, NY 14853
Neural Spectral Capacity: Measuring and Designing Architectures from Network Specification Alone
Sep 19, 2026Chenyu Zhu, Ruoyu Zhao, Zhichao LuNeural Architecture Performance Prediction Neural Architecture Search
Department of Computer Science, City University of Hong Kong
Efficient Architecture Search under Leave-One-Subject-Out Evaluation
Sep 18, 2026Heinke Hihn, Friedhelm SchwenkerNeural Architecture Search
IT and Engineering Department, IU International University of Applied Sciences, Berlin, Germany · Insitute for Neural Information Procressing, Ulm University, Ulm, Germany
ZAPS: Zero-Cost Active Proxy Search for Neural Architecture Search
Sep 12, 2026Hassan Touayouch, Rabie Najem, Mohammed BenjellounNeural Architecture Search Surrogate-Assisted Optimization
ENSICAEN · ISIA Lab, Université de Mons

Oct 26, 2026J/K move · Enter open · S save

TRON: Transferring Naturally Evolved Network Architectures into Neuroevolution

Konstantinos Zacharopoulos, Alexandra Bekou, Jose M Serradell, Foteini Paraskevopoulou+3

Technical University of Crete, ECE Department, Chania, 732 00, Greece · R.C. ATHENA, Industrial Systems Institute, Patras, 265 04, Greece · IBE, Institute of Evolutionary Biology (CSIC-Universitat Pompeu Fabra), Barcelona, 08003, Spain+1

Neural Architecture Search Neuroevolution

Open paper AskPDF arXiv

Neural architecture search (NAS) is challenging because of the vast, non-linear space of artificial neural network (ANN) topologies. Evolutionary methods can generate architectures, but their effectiveness is limited by difficulties in preserving functional organization during mutation and recombination. Naturally evolved biological networks may provide organizational principles that support adaptation and evolvability. Here, we introduce TRON (TRansfer Of Natural networks), a neuroevolution framework that uses experimentally characterized protein-protein interaction (PPI) networks as architectural priors. Instead of starting from random topologies, TRON reuses biological interaction patterns as structural building blocks. It combines classical evolutionary operators with neuroevolution-inspired mechanisms, including speciation, and introduces species quarantine to protect newly generated architectures during early maturation. We evaluated TRON against established evolutionary and neuroevolutionary methods on three classification benchmarks (CORA, CITESEER, and PUBMED) and three regression benchmarks (DIABETES, FRIEDMAN, and CALIFORNIA). TRON achieved the highest predictive performance among the evaluated methods on all classification datasets and most regression tasks. It showed substantially lower variability across independent runs, indicating greater robustness and convergence stability, at increased computational cost. These findings support the use of PPI networks as effective architectural priors and suggest that biologically derived interaction networks provide more favorable substrates for neuroevolution than random topologies. More broadly, TRON demonstrates the feasibility of transferring naturally evolved network architectures into artificial intelligence systems, offering a direction for improving evolvability in NAS through the reuse of biological organizational principles.