From Pragmas to Partners: A Symbiotic Evolution of Agentic High-Level Synthesis

2026-02-01

AI Summary

This work addresses the limitations of current high-level synthesis (HLS) tools—particularly in performance feedback, interface flexibility, and debuggability—that hinder their integration into agent-driven hardware design automation. The paper proposes positioning HLS as both an efficient abstraction layer and a golden reference for intelligent agents, establishing a symbiotic framework that evolves from human-in-the-loop collaboration toward fully autonomous design. It introduces the first taxonomy for co-evolution between agents and HLS, delineating a clear trajectory of responsibility transfer from assisted coding to autonomous design partnership. By leveraging large language model–powered agents, the approach specifically targets existing HLS bottlenecks, emphasizing rapid iteration, portability, and design variability. This study affirms the central role of HLS in autonomous hardware development and provides a foundational roadmap for future agent-augmented hardware design methodologies.

Technology Category

• Machine Learning: Hardware-aware ML
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Multiagent Systems: Adversarial Agents

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Agentic search

Abstract

The rise of large language models has sparked interest in AI-driven hardware design, raising the question: does high-level synthesis (HLS) still matter in the agentic era? We argue that HLS remains essential. While we expect mature agentic hardware systems to leverage both HLS and RTL, this paper focuses on HLS and its role in enabling agentic optimization. HLS offers faster iteration cycles, portability, and design permutability that make it a natural layer for agentic optimization. This position paper makes three contributions. First, we explain why HLS serves as a practical abstraction layer and a golden reference for agentic hardware design. Second, we identify key limitations of current HLS tools, namely inadequate performance feedback, rigid interfaces, and limited debuggability that agents are uniquely positioned to address. Third, we propose a taxonomy for the symbiotic evolution of agentic HLS, clarifying how responsibility shifts from human designers to AI agents as systems advance from copilots to autonomous design partners.

Problem

• high-level synthesis
• agentic hardware design
• performance feedback
• debuggability
• design automation

Innovation

• High-Level Synthesis
• Agentic AI
• Hardware Design Automation
• Symbiotic Evolution
• Design Abstraction