Neural Architecture Discovery via Autonomous Evolution
cs.AI
Submitted: 2025-07-24
Updated: 2026-10-08
Code: https://github.com/GAIR-NLP/ASI-Arch
Sources
- GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
- Language Models are Few-Shot Learners
- AdaEvolve: Adaptive LLM Driven Zeroth-Order Optimization
- AI4Research: A Survey of Artificial Intelligence for Scientific Research
- Language Modeling by Language Models
- Rethinking Attention with Performers
- BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions
- Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
- Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality
- Mamba: Linear-Time Sequence Modeling with Selective State Spaces
- ShinkaEvolve: Towards Open-Ended And Sample-Efficient Program Evolution
- Jamba: A Hybrid Transformer-Mamba Language Model
- Pointer Sentinel Mixture Models
- LLMatic: Neural Architecture Search via Large Language Models and Quality Diversity Optimization
- AlphaEvolve: A coding agent for scientific and algorithmic discovery
- GPT-4 Technical Report
- The LAMBADA dataset: Word prediction requiring a broad discourse context
- RWKV: Reinventing RNNs for the Transformer Era
- cosFormer: Rethinking Softmax in Attention
- HGRN2: Gated Linear RNNs with State Expansion
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems