David vs. Goliath: Can Small Models Win Big with Agentic AI in Hardware Design?
By: Shashwat Shankar , Subhranshu Pandey , Innocent Dengkhw Mochahari and more
Potential Business Impact:
Makes AI design chips faster and cheaper.
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.
Similar Papers
Revolution or Hype? Seeking the Limits of Large Models in Hardware Design
Machine Learning (CS)
AI helps design computer chips faster and better.
Small Language Models are the Future of Agentic AI
Artificial Intelligence
Smaller AI models can do many jobs cheaper.
Can Small GenAI Language Models Rival Large Language Models in Understanding Application Behavior?
Software Engineering
Small AI models find computer viruses efficiently.