mlsanityData to 14 Oct 2026

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

arXiv 2512.05073 ↗First posted 4 Dec 2025cs.LG cs.AI cs.ARcited by 1

On the map: LLM agents and tool use → Software engineering coding agents

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.

Key facts. Cited by 1 paper 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.

Builds on

19 of 39 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025MCP4EDA: LLM-Powered Model Context Protocol RTL-to-GDSII Automation with Backend Aware Synthesis Optimization25 Jul
  2. 2025ORFS-agent: Tool-Using Agents for Chip Design Optimization10 Jun
  3. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation16 Aug

Other references · 16

  1. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  2. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,915
  3. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,795
  4. 2024Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phonecited by 1,917
  5. 2025Small Language Models are the Future of Agentic AIcited by 270
  6. 2023VerilogEval: Evaluating Large Language Models for Verilog Code Generationcited by 252
  7. 2023VeriGen: A Large Language Model for Verilog Code Generationcited by 200
  8. 2023ChipNeMo: Domain-Adapted LLMs for Chip Designcited by 174
  9. 2024BetterV: Controlled Verilog Generation with Discriminative Guidancecited by 100
  10. 2025How Hungry is AI? Benchmarking Energy, Water, and Carbon Footprint of LLM Inferencecited by 76
  11. 2024CodeV: Empowering LLMs with HDL Generation through Multi-Level Summarizationcited by 38
  12. 2025Spec2RTL-Agent: Automated Hardware Code Generation from Complex Specifications Using LLM Agent Systemscited by 18
4 more
  1. 2024AssertionBench: A Benchmark to Evaluate Large-Language Models for Assertion Generationcited by 16
  2. 2025Intelligence per Watt: Measuring Intelligence Efficiency of Local AIcited by 14
  3. 2025Revolution or Hype? Seeking the Limits of Large Models in Hardware Designcited by 9
  4. 2024ChipAlign: Instruction Alignment in Large Language Models for Chip Design via Geodesic Interpolationcited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Complexity Horizons of Compressed Models in Analog Circuit Analysiscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026D2K-Bench: Can LLM Agents Turn Expert Designs into Efficient GPU Kernels?
  2. 2026Agentic Architect: An Agentic AI Framework for Architecture Design Exploration and Optimization
  3. 2026Hardware Co-Design Scaling Laws via Roofline Modelling for On-Device LLMs
  4. 2025STARK: Strategic Team of Agents for Refining Kernels
  5. 2026AI Hardware Accelerators for Large Language Models: Architectures and the Memory Wall ↗
  6. 2026KernelCraft: Benchmarking for Agentic Close-to-Metal Kernel Generation on Emerging Hardware
  7. 2025Can Reasoning Models Reason about Hardware? An Agentic HLS Perspective
  8. 2026Is Agentic AI Ready for Real-World Hardware Engineering? A Deep Dive with Phoenix-bench