[Paper] Multi-Objective Coevolution of Prompts and Templates for Circuit Approximation

Source: arXiv - 2606.13089v1

Overview

Approximate multipliers deliberately relax computational accuracy to achieve gains in power efficiency, latency, and silicon area, which makes them well-suited for error-resilient applications such as neural networks. In this work, we introduce a co-evolutionary algorithm that leverages an off-the-shelf large language model (LLM) without requiring domain-specific training to automate the design of optimized 8-bit approximate multipliers. The approach simultaneously evolves a population of candidate circuits and a population of prompt templates that steer LLM-driven modifications. Experimental results for several target design objectives demonstrate that the proposed method discovers approximate multipliers with improved error-area trade-offs compared to highly optimized circuits from the EvoApproxLib library.

Key Contributions

This paper presents research in the following areas:

• cs.NE

Methodology

Please refer to the full paper for detailed methodology.

Practical Implications

This research contributes to the advancement of cs.NE.

Authors

• Martin Tomasovic
• Lukas Sekanina

Paper Information

• arXiv ID: 2606.13089v1
• Categories: cs.NE
• Published: June 11, 2026
• PDF: Download PDF