CLARPLMar 17

CODMAS: A Dialectic Multi-Agent Collaborative Framework for Structured RTL Optimization

arXiv:2603.1720415.01 citationsh-index: 16
AI Analysis

This addresses the challenge of improving power, performance, and area (PPA) in chip design, offering a novel approach for EDA engineers, though it is incremental in applying multi-agent reasoning to a specific domain.

The paper tackles the problem of automating Register Transfer Level (RTL) code optimization for Electronic Design Automation (EDA) by introducing CODMAS, a multi-agent framework that achieves approximately 25% reduction in critical path delay for pipelining and 22% power reduction for clock gating, while reducing functional and compilation failures compared to baselines.

Optimizing Register Transfer Level (RTL) code is a critical step in Electronic Design Automation (EDA) for improving power, performance, and area (PPA). We present CODMAS (Collaborative Optimization via a Dialectic Multi-Agent System), a framework that combines structured dialectic reasoning with domain-aware code generation and deterministic evaluation to automate RTL optimization. At the core of CODMAS are two dialectic agents: the Articulator, inspired by rubber-duck debugging, which articulates stepwise transformation plans and exposes latent assumptions; and the Hypothesis Partner, which predicts outcomes and reconciles deviations between expected and actual behavior to guide targeted refinements. These agents direct a Domain-Specific Coding Agent (DCA) to generate architecture-aware Verilog edits and a Code Evaluation Agent (CEA) to verify syntax, functionality, and PPA metrics. We introduce RTLOPT, a benchmark of 120 Verilog triples (unoptimized, optimized, testbench) for pipelining and clock-gating transformations. Across proprietary and open LLMs, CODMAS achieves ~25% reduction in critical path delay for pipelining and ~22% power reduction for clock gating, while reducing functional and compilation failures compared to strong prompting and agentic baselines. These results demonstrate that structured multi-agent reasoning can significantly enhance automated RTL optimization and scale to more complex designs and broader optimization tasks.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes