MultiGA: Leveraging Multi-Source Seeding in Genetic Algorithms

2025/11/21 by Ng, Isabelle Diana May-Xin, Weerasooriya, Tharindu Cyril, Zhu, Haitao +1
Computer Science · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Multimodal Machine Learning Applications #Natural Language Processing Techniques #Neural and Evolutionary Computing (cs.NE) #Topic Modeling

paper · doi:10.48550/arxiv.2512.04097

openalex publication_date 2025/11/21 · openalex created_date 2025/12/06 · openalex updated_date 2026/07/28

Abstract

In this paper, we introduce, MultiGA, an optimization framework 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 of candidate solutions. MultiGA generates a range of outputs from various parent LLMs 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. Our results show that MultiGA produces high accuracy across multiple benchmarks, 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.

Citations

• A Hybrid GA LLM Framework for Structured Task Optimization
• Qwen3 Technical Report
• GAAPO: Genetic Algorithmic Applied to Prompt Optimization
• Evolving Deeper LLM Thinking
• Multi-Agent Collaboration Mechanisms: A Survey of LLMs
• LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods
• Justice or Prejudice? Quantifying Biases in LLM-as-a-Judge
• Understanding the Importance of Evolutionary Search in Automated Heuristic Design with Large Language Models
• NATURAL PLAN: Benchmarking LLMs on Natural Language Planning
• TravelPlanner: A Benchmark for Real-World Planning with Language Agents
• GPQA: A Graduate-Level Google-Proof Q&A Benchmark
• An In-depth Survey of Large Language Model-based Artificial Intelligence Agents
• Tree of Thoughts: Deliberate Problem Solving with Large Language Models
• Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs
• Self-Refine: Iterative Refinement with Self-Feedback
• LLaMA: Open and Efficient Foundation Language Models
• Large Language Models Are Human-Level Prompt Engineers
• Evolution through Large Models
• Impossible Triangle: What's Next for Pre-trained Language Models?
• Training language models to follow instructions with human feedback
• BNAI, NO-TOKEN, and MIND-UNITY: Pillars of a Systemic Revolution in Artificial Intelligence
• BBQ: A Hand-Built Bias Benchmark for Question Answering
• Language Models are Few-Shot Learners
• RoBERTa: A Robustly Optimized BERT Pretraining Approach
• A Survey on Neural Architecture Search
• SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems
• HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering
• TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for\n Reading Comprehension
• Illuminating search spaces by mapping elites
• AI Benchmark Half-Life in Recursive Corpora: A Theory of Validity Decay under Semantic Leakage and Regeneration
• BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Related

• Lyria: A Genetic Algorithm-Driven Neuro-Symbolic Reasoning Framework for LLMs
• GAAPO: Genetic Algorithmic Applied to Prompt Optimization
• Evolutionary Computation and Large Language Models: A Survey of Methods, Synergies, and Applications
• Evolutionary thoughts: integration of large language models and evolutionary algorithms
• Evolving Code with A Large Language Model