# AgRefactor: Self-Evolving Agentic Workflow for HLS Compatibility and Performance

arXiv: https://arxiv.org/abs/2606.30949 · HTML: https://mlsanity.com/paper/2606.30949/

## Key facts

- Cited by 2 papers 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 16 of its 33 references that are in the map.
- First posted on arXiv 29 Jun 2026.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)
- Synthetic data and self-improvement for LLMs / [Self-evolving LLM agents](https://mlsanity.com/synth/self-evolving-llm-agents/)

## Builds on (most cited first, 16 of 16)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [A-MEM: Agentic Memory for LLM Agents](https://mlsanity.com/paper/2502.12110/) (2025)
- [AlphaEvolve: A coding agent for scientific and algorithmic discovery](https://mlsanity.com/paper/2506.13131/) (2025)
- [Agent Workflow Memory](https://mlsanity.com/paper/2409.07429/) (2024)
- [MEMORYLLM: Towards Self-Updatable Large Language Models](https://mlsanity.com/paper/2402.04624/) (2024)
- [AutoDSE: Enabling Software Programmers to Design Efficient FPGA Accelerators](https://mlsanity.com/paper/2009.14381/) (2020)
- [ScaleHLS: A New Scalable High-Level Synthesis Framework on Multi-Level Intermediate Representation](https://mlsanity.com/paper/2107.11673/) (2021)
- [Allo: A Programming Model for Composable Accelerator Design](https://mlsanity.com/paper/2404.04815/) (2024)
- [C2HLSC: Can LLMs Bridge the Software-to-Hardware Design Gap?](https://mlsanity.com/paper/2406.09233/) (2024)
- [HIDA: A Hierarchical Dataflow Compiler for High-Level Synthesis](https://mlsanity.com/paper/2311.03379/) (2023)
- [HLSFactory: A Framework Empowering High-Level Synthesis Datasets for Machine Learning and Beyond](https://mlsanity.com/paper/2405.00820/) (2024)
- [A Unified Framework for Automated Code Transformation and Pragma Insertion](https://mlsanity.com/paper/2405.03058/) (2024)
- [Stream-HLS: Towards Automatic Dataflow Acceleration](https://mlsanity.com/paper/2501.09118/) (2025)
- [LightningSimV2: Faster and Scalable Simulation for High-Level Synthesis via Graph Compilation and Optimization](https://mlsanity.com/paper/2404.09471/) (2024)
- [Holistic Optimization Framework for FPGA Accelerators](https://mlsanity.com/paper/2501.09242/) (2025)

## Built on by (most cited first, 2 of 2)

- [HLSmith: An Expert-Guided Agentic Framework for C/C++-to-HLS Translation](https://mlsanity.com/paper/2608.06791/) (2026)
- [Can Agents Design Better Chips with a Higher Level Abstraction?](https://mlsanity.com/paper/2609.21157/) (2026)

## Abstract (arXiv)

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.