# MACO: A Multi-Agent LLM Framework for Automated CGRA Hardware/Software Co-Design

arXiv: https://arxiv.org/abs/2509.13557 · HTML: https://mlsanity.com/paper/2509.13557/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Sep 2025.

## Built on by (most cited first, 1 of 1)

- [CorrectHDL: Agentic HDL Design with LLMs Leveraging High-Level Synthesis as Reference](https://mlsanity.com/paper/2511.16395/) (2025)

## Abstract (arXiv)

Designing optimal Coarse-Grained Reconfigurable Arrays (CGRAs) requires navigating a vast, interdependent hardware/software space bottlenecked by costly manual iteration. We present MACO, an open-source, multi-agent LLM framework that automates CGRA HW/SW co-design. MACO decomposes the design loop into four collaborative stages, HW/SW Co-design, Error Correction, Best-Design Selection, and Evaluation & Feedback, to iteratively optimize power, performance, and area (PPA). To accelerate convergence and efficiently traverse the design space, MACO introduces an exponentially decaying exploration strategy, EDA-guided LLM self-learning, and robust rule-based error correction. Evaluated against state-of-the-art baselines, MACO reduces power consumption by 25.9%, improves performance by 20.0%, and accelerates the search process by 5x. Finally, we validate MACO's physical design through a complete 7nm ASIC design flow.