# David vs. Goliath: Can Small Models Win Big with Agentic AI in Hardware Design?

arXiv: https://arxiv.org/abs/2512.05073 · HTML: https://mlsanity.com/paper/2512.05073/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 19 of its 39 references that are in the map.
- First posted on arXiv 4 Dec 2025.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 19 of 19)

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone](https://mlsanity.com/paper/2404.14219/) (2024)
- [Small Language Models are the Future of Agentic AI](https://mlsanity.com/paper/2506.02153/) (2025)
- [VerilogEval: Evaluating Large Language Models for Verilog Code Generation](https://mlsanity.com/paper/2309.07544/) (2023)
- [VeriGen: A Large Language Model for Verilog Code Generation](https://mlsanity.com/paper/2308.00708/) (2023)
- [ChipNeMo: Domain-Adapted LLMs for Chip Design](https://mlsanity.com/paper/2311.00176/) (2023)
- [BetterV: Controlled Verilog Generation with Discriminative Guidance](https://mlsanity.com/paper/2402.03375/) (2024)
- [How Hungry is AI? Benchmarking Energy, Water, and Carbon Footprint of LLM Inference](https://mlsanity.com/paper/2505.09598/) (2025)
- [CodeV: Empowering LLMs with HDL Generation through Multi-Level Summarization](https://mlsanity.com/paper/2407.10424/) (2024)
- [Spec2RTL-Agent: Automated Hardware Code Generation from Complex Specifications Using LLM Agent Systems](https://mlsanity.com/paper/2506.13905/) (2025)
- [AssertionBench: A Benchmark to Evaluate Large-Language Models for Assertion Generation](https://mlsanity.com/paper/2406.18627/) (2024)
- [ORFS-agent: Tool-Using Agents for Chip Design Optimization](https://mlsanity.com/paper/2506.08332/) (2025)
- [Intelligence per Watt: Measuring Intelligence Efficiency of Local AI](https://mlsanity.com/paper/2511.07885/) (2025)
- [MCP4EDA: LLM-Powered Model Context Protocol RTL-to-GDSII Automation with Backend Aware Synthesis Optimization](https://mlsanity.com/paper/2507.19570/) (2025)
- [Revolution or Hype? Seeking the Limits of Large Models in Hardware Design](https://mlsanity.com/paper/2509.04905/) (2025)
- [ChipAlign: Instruction Alignment in Large Language Models for Chip Design via Geodesic Interpolation](https://mlsanity.com/paper/2412.19819/) (2024)

## Built on by (most cited first, 1 of 1)

- [Complexity Horizons of Compressed Models in Analog Circuit Analysis](https://mlsanity.com/paper/2605.02285/) (2026)

## Abstract (arXiv)

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.