LLM Agents To Refactor Software For High Level Synthesis (Carnegie Mellon, UCLA)

Researchers from Carnegie Mellon University and UCLA published a technical paper titled “AgRefactor: Self-Evolving Agentic Workflow for HLS Compatibility and Performance.” The paper introduces an “LLM-based multi-agent workflow  for refactoring software into HLS-compatible programs” and reports a 6.51× geometric mean speedup over a state-of-the-art pragma tuning tool. Find the technical paper here . June 2026. Zou, Yang, Zijian Ding, Yizhou Sun, and Jason Cong. “AgRefactor: Self-Evolving Agentic