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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chang, Che-Ming, Vijayaraghavan, Prashanth, Jadhav, Ashutosh, Mackin, Charles, Mukherjee, Vandana, Tsai, Hsinyu, Degan, Ehsan
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908896494354432
author Chang, Che-Ming
Vijayaraghavan, Prashanth
Jadhav, Ashutosh
Mackin, Charles
Mukherjee, Vandana
Tsai, Hsinyu
Degan, Ehsan
author_facet Chang, Che-Ming
Vijayaraghavan, Prashanth
Jadhav, Ashutosh
Mackin, Charles
Mukherjee, Vandana
Tsai, Hsinyu
Degan, Ehsan
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2603_17204
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle CODMAS: A Dialectic Multi-Agent Collaborative Framework for Structured RTL Optimization
Chang, Che-Ming
Vijayaraghavan, Prashanth
Jadhav, Ashutosh
Mackin, Charles
Mukherjee, Vandana
Tsai, Hsinyu
Degan, Ehsan
Computation and Language
Hardware Architecture
Programming Languages
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.
title CODMAS: A Dialectic Multi-Agent Collaborative Framework for Structured RTL Optimization
topic Computation and Language
Hardware Architecture
Programming Languages
url https://arxiv.org/abs/2603.17204