MultiGA: Leveraging Multi-Source Seeding in Genetic Algorithms
By: Isabelle Diana May-Xin Ng , Tharindu Cyril Weerasooriya , Haitao Zhu and more
Potential Business Impact:
Combines many AI minds to solve hard problems.
Large Language Models (LLMs) are widely used across research domains to tackle complex tasks, but their performance can vary significantly depending on the task at hand. Evolutionary algorithms, inspired by natural selection, can be used to refine solutions iteratively at inference-time. To the best of our knowledge, there has not been exploration on leveraging the collective capabilities of multi-source seeding for LLM-guided genetic algorithms. In this paper, we introduce a novel approach, MultiGA, which applies genetic algorithm principles to address complex natural language tasks and reasoning problems by sampling from a diverse population of LLMs to initialize the population. MultiGA generates a range of outputs from various parent LLMs, open source and closed source, and uses a neutral fitness function to evaluate them. Through an iterative recombination process, we mix and refine these generations until an optimal solution is achieved. We benchmark our approach using text-to-SQL code generation tasks, trip planning, GPQA benchmark for grad-level science questions, and the BBQ bias benchmark. Our results show that MultiGA converges to the accuracy of the LLM best fit for the task, and these insights lay the foundation for future research looking closer at integrating multiple LLMs for unexplored tasks in which selecting only one pre-trained model is unclear or suboptimal.
Similar Papers
Evolutionary thoughts: integration of large language models and evolutionary algorithms
Neural and Evolutionary Computing
AI learns faster by trying many ideas.
LLM-Guided Evolution: An Autonomous Model Optimization for Object Detection
Neural and Evolutionary Computing
Makes AI better at finding objects in pictures.
LLM-Based Instance-Driven Heuristic Bias In the Context of a Biased Random Key Genetic Algorithm
Neural and Evolutionary Computing
Helps computers solve hard problems faster.