# Can Reasoning Models Reason about Hardware? An Agentic HLS Perspective

arXiv: https://arxiv.org/abs/2503.12721 · HTML: https://mlsanity.com/paper/2503.12721/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 12 of its 17 references that are in the map.
- First posted on arXiv 17 Mar 2025.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)
- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 12 of 12)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation](https://mlsanity.com/paper/2305.01210/) (2023)
- [Asleep at the Keyboard? Assessing the Security of GitHub Copilot's Code Contributions](https://mlsanity.com/paper/2108.09293/) (2021)
- [AutoChip: Automating HDL Generation Using LLM Feedback](https://mlsanity.com/paper/2311.04887/) (2023)
- [HLSPilot: LLM-based High-Level Synthesis](https://mlsanity.com/paper/2408.06810/) (2024)
- [Rome was Not Built in a Single Step: Hierarchical Prompting for LLM-based Chip Design](https://mlsanity.com/paper/2407.18276/) (2024)
- [Automated C/C++ Program Repair for High-Level Synthesis via Large Language Models](https://mlsanity.com/paper/2407.03889/) (2024)
- [C2HLSC: Can LLMs Bridge the Software-to-Hardware Design Gap?](https://mlsanity.com/paper/2406.09233/) (2024)
- [Evaluating LLMs for Hardware Design and Test](https://mlsanity.com/paper/2405.02326/) (2024)
- [Automatic Hardware Pragma Insertion in High-Level Synthesis: A Non-Linear Programming Approach](https://mlsanity.com/paper/2405.12304/) (2024)
- [Evaluating Large Language Models for Automatic Register Transfer Logic Generation via High-Level Synthesis](https://mlsanity.com/paper/2408.02793/) (2024)

## Built on by (most cited first, 9 of 9)

- [iDSE: Navigating Design Space Exploration in High-Level Synthesis Using LLMs](https://mlsanity.com/paper/2505.22086/) (2025)
- [MARVEL: Multi-Agent RTL Vulnerability Extraction using Large Language Models](https://mlsanity.com/paper/2505.11963/) (2025)
- [CorrectHDL: Agentic HDL Design with LLMs Leveraging High-Level Synthesis as Reference](https://mlsanity.com/paper/2511.16395/) (2025)
- [Bench4HLS: End-to-End Evaluation of LLMs in High-Level Synthesis Code Generation](https://mlsanity.com/paper/2601.19941/) (2026)
- [Agent Factories for High Level Synthesis: How Far Can General-Purpose Coding Agents Go in Hardware Optimization?](https://mlsanity.com/paper/2603.25719/) (2026)
- [LLMs for Secure Hardware Design and Related Problems: Opportunities and Challenges](https://mlsanity.com/paper/2605.10807/) (2026)
- [Evidence-Driven LLM Agent for C-to-Synthesizable-C Conversion and Verification](https://mlsanity.com/paper/2606.28409/) (2026)
- [From Pragmas to Partners: A Symbiotic Evolution of Agentic High-Level Synthesis](https://mlsanity.com/paper/2602.01401/) (2026)
- [Do AI Agents Understand Computer Architecture?](https://mlsanity.com/paper/2609.19387/) (2026)

## Abstract (arXiv)

Recent Large Language Models (LLMs) such as OpenAI o3-mini and DeepSeek-R1 use enhanced reasoning through Chain-of-Thought (CoT). Their potential in hardware design, which relies on expert-driven iterative optimization, remains unexplored. This paper investigates whether reasoning LLMs can address challenges in High-Level Synthesis (HLS) design space exploration and optimization. During HLS, engineers manually define pragmas/directives to balance performance and resource constraints. We propose an LLM-based optimization agentic framework that automatically restructures code, inserts pragmas, and identifies optimal design points via feedback from HLs tools and access to integer-linear programming (ILP) solvers. Experiments compare reasoning models against conventional LLMs on benchmarks using success rate, efficiency, and design quality (area/latency) metrics, and provide the first-ever glimpse into the CoTs produced by a powerful open-source reasoning model like DeepSeek-R1.