{"slug": "hlsmith-an-expert-guided-agentic-framework-for-c-c-to-hls-translation", "title": "HLSmith: An Expert-Guided Agentic Framework for C/C++-to-HLS Translation", "summary": "Researchers introduced HLSmith, an expert-guided agentic framework that translates C/C++ programs into optimized high-level synthesis (HLS) accelerators, achieving a geometric mean speedup of 4.24x over the prior ChatHLS framework on PolyBench while producing functionally correct designs for every benchmark, compared with ChatHLS's 57% valid-design rate. HLSmith combines an HLS optimization expertise library, a staged feedback-driven orchestration flow, and a tool-grounded model-adaptation pipeline, reaching speedups up to 252x with commercial frontier models and 138x with open-weight models.", "body_md": "# Computer Science > Hardware Architecture\n\n[Submitted on 7 Aug 2026]\n\n# Title:HLSmith: An Expert-Guided Agentic Framework for C/C++-to-HLS Translation\n\n[View PDF](/pdf/2608.06791)\n\n[HTML (experimental)](https://arxiv.org/html/2608.06791v1)\n\nAbstract:Application-specific FPGA accelerators offer substantial performance and energy-efficiency gains across many application domains, but developing them is costly, often requiring months of specialized effort. Even with high-level synthesis (HLS), designers still need extensive hardware expertise to build high-performance accelerators. Although large language models (LLMs) have demonstrated strong software-generation capabilities, even frontier models lack the hardware intuition and procedural knowledge needed to reliably translate baseline C/C++ programs into high-performance HLS designs: they struggle to identify effective architectures, follow the optimization processes used by HLS experts, and apply hardware transformations consistently across diverse kernels. We present HLSmith, an expert-guided framework for translating C/C++ programs into optimized HLS accelerators. HLSmith combines three components: an HLS optimization expertise library that encodes guarded transformation recipes, their applicability and prerequisite conditions, and unsafe cases to avoid; a staged, feedback-driven orchestration flow modeled on expert HLS development practice that guides agents through synthesis, bottleneck analysis, and optimization; and a tool-grounded model-adaptation pipeline that converts optimization trajectories from commercial frontier models into training data for fine-tuning open-weight LLMs. We evaluate HLSmith on PolyBench against ChatHLS, a leading prior agent-orchestration framework for HLS accelerator development. HLSmith achieves a geometric mean speedup of 4.24x over ChatHLS while producing functionally correct designs, in both software and RTL simulation, for every benchmark, compared with ChatHLS's 57% valid-design rate. It further reaches speedups of up to 252x and 138x with commercial frontier models and open-weight models, respectively.\n\n### References & Citations\n\nLoading...\n\n# Bibliographic and Citation Tools\n\nBibliographic Explorer\n\n*(*[What is the Explorer?](https://info.arxiv.org/labs/showcase.html#arxiv-bibliographic-explorer))\nConnected Papers\n\n*(*[What is Connected Papers?](https://www.connectedpapers.com/about))\nLitmaps\n\n*(*[What is Litmaps?](https://www.litmaps.co/))\nscite Smart Citations\n\n*(*[What are Smart Citations?](https://www.scite.ai/))# Code, Data and Media Associated with this Article\n\nalphaXiv\n\n*(*[What is alphaXiv?](https://alphaxiv.org/))\nCatalyzeX Code Finder for Papers\n\n*(*[What is CatalyzeX?](https://www.catalyzex.com))\nDagsHub\n\n*(*[What is DagsHub?](https://dagshub.com/))\nGotit.pub\n\n*(*[What is GotitPub?](http://gotit.pub/faq))\nHugging Face\n\n*(*[What is Huggingface?](https://huggingface.co/huggingface))\nScienceCast\n\n*(*[What is ScienceCast?](https://sciencecast.org/welcome))# Demos\n\n# Recommenders and Search Tools\n\nInfluence Flower\n\n*(*[What are Influence Flowers?](https://influencemap.cmlab.dev/))\nCORE Recommender\n\n*(*[What is CORE?](https://core.ac.uk/services/recommender))# arXivLabs: experimental projects with community collaborators\n\narXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.\n\nBoth individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.\n\nHave an idea for a project that will add value for arXiv's community? [ Learn more about arXivLabs](https://info.arxiv.org/labs/index.html).", "url": "https://wpnews.pro/news/hlsmith-an-expert-guided-agentic-framework-for-c-c-to-hls-translation", "canonical_source": "https://arxiv.org/abs/2608.06791", "published_at": "2026-08-10 13:52:10+00:00", "updated_at": "2026-08-10 14:11:37.229122+00:00", "lang": "en", "topics": ["artificial-intelligence", "machine-learning", "large-language-models", "ai-research", "ai-agents"], "entities": ["HLSmith", "ChatHLS", "PolyBench", "arXiv"], "alternates": {"html": "https://wpnews.pro/news/hlsmith-an-expert-guided-agentic-framework-for-c-c-to-hls-translation", "markdown": "https://wpnews.pro/news/hlsmith-an-expert-guided-agentic-framework-for-c-c-to-hls-translation.md", "text": "https://wpnews.pro/news/hlsmith-an-expert-guided-agentic-framework-for-c-c-to-hls-translation.txt", "jsonld": "https://wpnews.pro/news/hlsmith-an-expert-guided-agentic-framework-for-c-c-to-hls-translation.jsonld"}}