A co-evolutionary method evolves LLM prompts and circuits to produce 8-bit approximate multipliers with better error-area trade-offs than EvoApproxLib.
In: Proc of the Genetic and Evolutionary Computation Conference
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
LLM code generation research overemphasizes security and performance while practitioners worry most about maintainability and technical debt, and prompt-based optimization of these qualities proves unstable in practice.
citing papers explorer
-
Multi-Objective Coevolution of Prompts and Templates for Circuit Approximation
A co-evolutionary method evolves LLM prompts and circuits to produce 8-bit approximate multipliers with better error-area trade-offs than EvoApproxLib.
-
Quality Assurance of LLM-generated Code: Addressing Non-Functional Quality Characteristics
LLM code generation research overemphasizes security and performance while practitioners worry most about maintainability and technical debt, and prompt-based optimization of these qualities proves unstable in practice.