AI RESEARCH

From Memorization to Creativity: LLM as a Designer of Novel Neural Architectures

arXiv CS.LG

ArXi:2601.02997v2 Announce Type: replace Large language models (LLMs) excel in program synthesis, yet their capacity for neural architecture design -- balancing syntactic reliability, performance, and structural novelty -- remains underexplored. We present a closed-loop architecture synthesis pipeline within the NNGPT framework, in which a code-oriented LLM evolves over 22 supervised fine-tuning cycles.