Large Language Model(LLM) inference demands massive compute and energy, making domain-specific tasks expensive and unsustainable. As foundation models keep scaling, we ask: Is bigger always better for hardware design? Our work tests this by evaluating Small Language Models coupled with a curated agentic AI framework on NVIDIA's Comprehensive Verilog Design Problems(CVDP) benchmark. Results show that agentic workflows: through task decomposition, iterative feedback, and correction - not only unlock near-LLM performance at a fraction of the cost but also create learning opportunities for agents, paving the way for efficient, adaptive solutions in complex design tasks.
@article{arxiv.2512.05073,
title = {David vs. Goliath: Can Small Models Win Big with Agentic AI in Hardware Design?},
author = {Shashwat Shankar and Subhranshu Pandey and Innocent Dengkhw Mochahari and Bhabesh Mali and Animesh Basak Chowdhury and Sukanta Bhattacharjee and Chandan Karfa},
journal= {arXiv preprint arXiv:2512.05073},
year = {2025}
}