{"ID":2833136,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.05073","arxiv_id":"2512.05073","title":"David vs. Goliath: Can Small Models Win Big with Agentic AI in Hardware Design?","abstract":"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.","short_abstract":"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...","url_abs":"https://arxiv.org/abs/2512.05073","url_pdf":"https://arxiv.org/pdf/2512.05073v1","authors":"[\"Shashwat Shankar\",\"Subhranshu Pandey\",\"Innocent Dengkhw Mochahari\",\"Bhabesh Mali\",\"Animesh Basak Chowdhury\",\"Sukanta Bhattacharjee\",\"Chandan Karfa\"]","published":"2025-12-04T18:37:29Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AI\",\"cs.AR\",\"cs.SE\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}