AgRefactor: Self-Evolving Agentic Workflow for HLS Compatibility and Performance
Quick Answer
AgRefactor is an LLM-based multi-agent workflow that refactors software into HLS-compatible code, achieving a 6.51x speedup over state-of-the-art tools on complex benchmarks.
Quick Take
It utilizes a self-evolving memory system to enhance efficiency and scalability, outperforming existing methods on 9 out of 11 challenging real-world cases. Fully automated and open-sourced, it addresses the gap between software and hardware programming practices.
Key Points
- AgRefactor integrates automated refactoring tools for cost reduction and scalability.
- It outperforms or matches state-of-the-art tools on 9 out of 11 benchmarks.
- Achieves a 6.51x speedup over the leading pragma tuning tool.
- Utilizes a self-evolving memory system for improved task handling.
- Fully automated and open-sourced for broader accessibility.
Paper Resources
📖 Reader Mode
~2 min readAbstract:High-Level Synthesis (HLS) provides a fast path from concepts to silicon, but converting real-world software into synthesizable HLS code remains challenging due to restrictive language support and the gap between software and hardware programming practices. Existing automated and LLM-based refactoring approaches partially address this problem, yet they often lack flexibility, struggle to scale, and incur high computational costs. We introduce AgRefactor, an LLM-based multi-agent workflow for refactoring software into HLS-compatible programs. AgRefactor incorporates a self-evolving memory system that accumulates and retrieves factual and strategic knowledge across tasks, improving robustness and efficiency on unseen programs. To reduce cost and enhance scalability, it integrates automated refactoring tools, enabling agents to balance LLM-driven rewrites with efficient tool-based transformations. On 9 out of 11 challenging real-world benchmarks, which are 5-10x longer than the most complex cases studied in prior work, AgRefactor outperforms or matches the state-of-the-art automated refactoring tool and a strong LLM-based baseline built on the same framework backbone. Further agentic performance optimization yields a 6.51x geometric mean speedup over the SoTA pragma tuning tool and a 1.20x speedup over optimized open-source designs with less than 20% extra resources. AgRefactor is fully-automated and open-sourced.
| Subjects: | Artificial Intelligence (cs.AI); Hardware Architecture (cs.AR) |
| Cite as: | arXiv:2606.30949 [cs.AI] |
| (or arXiv:2606.30949v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2606.30949 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yang Zou [view email]
[v1]
Mon, 29 Jun 2026 22:02:34 UTC (774 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →HOBA: Hierarchical On-Policy Bidding Agents for Adaptive Online Advertising
HOBA (Hierarchical On-policy Bidding Agents) is a novel hierarchical reinforcement learning framework that enhances online advertising bidding systems by improving adaptability and reducing hyperparameter tuning costs. It utilizes a for hyperparameter inference, a SARSA agent for expert model selection, and a dynamic expert pool for bid execution, achieving a +3.6% increase in target cost during large-scale deployment and outperforming state-of-the-art baselines on AuctionNet.