Metraipolis › archive › dc_40282c7f2abb
HLSClaw: Bringing Vibe Coding to High-Level Synthesis through Skill-Based Agentic Harness — arXiv:2611.02784
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.02784
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T11:22:54.171Z
- SHA-256 of the archived text
e1ae46401f65e239ed1e066811551f9a40b3bc15c313ce3443479c7d4d41bf1e- Stable URL of this page
https://metraipolis.com/documento/dc_40282c7f2abb
How to cite
HLSClaw: Bringing Vibe Coding to High-Level Synthesis through Skill-Based Agentic Harness — arXiv:2611.02784 — arXiv (en), https://arxiv.org/abs/2611.02784 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_40282c7f2abb (Metraipolis archive dc_40282c7f2abb, sha256 e1ae46401f65e239ed1e066811551f9a40b3bc15c313ce3443479c7d4d41bf1e)
BibTeX
@misc{dc40282c7f2abb,
title = {HLSClaw: Bringing Vibe Coding to High-Level Synthesis through Skill-Based Agentic Harness — arXiv:2611.02784},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.02784},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_40282c7f2abb; sha256 e1ae46401f65e239ed1e066811551f9a40b3bc15c313ce3443479c7d4d41bf1e},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.02784. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
LLM agents are rapidly shifting software development toward intent-driven \emph{vibe coding}, yet their effectiveness drops sharply in high-level synthesis (HLS), where code optimization must jointly consider design structure, directive search, and downstream hardware constraints. Existing HLS optimization approaches, including both heuristic-based methods and recent LLM-assisted pipelines, typically operate at fixed abstraction levels or in weakly coupled stages, limiting their ability to leverage the strong interplay between source code restructuring and directive search outcomes. Our key insight is that HLS optimization can be reframed from a fixed, hardwired transformation pipeline into a skill-based agentic control problem: an LLM agent equipped with modular, executable optimization skills and a feedback-driven orchestrator can autonomously navigate the coupled space of code restructuring and directive search. This motivates the design of HLSClaw, the first HLS-specific, skill-based agentic harness for holistic HLS optimization. On real-world HLS benchmarks, HLSClaw achieves a 39.12x geometric-mean latency speedup, outperforming the compiler baseline ScaleHLS by 1.98x, and surpassing the commercial coding agents Claude Code and Codex by 1.86x and 1.70x, respectively, while maintaining strong timing robustness.
Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Software Engineering (cs.SE).
Pagina del lavoro: https://arxiv.org/abs/2611.02784 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-03T11:02:37.639Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).