We are thrilled to announce an exciting special session at EvoStar 2025: EvoLLMs: Integrating Evolutionary Computing with Large Language Models. This session will delve into the innovative intersection of large language models (LLMs) and evolutionary computing (EC), a frontier in AI and computational intelligence that is rapidly gaining traction.
Official website: https://www.evostar.org/2025/evoapps/evollms/
EvoLLMs: Integrating Evolutionary Computing with Large Language Models
The integration of LLMs with EC offers immense potential across a variety of domains—from enhancing optimization processes to creating more adaptive and robust systems. This special session will explore how LLMs can aid in guiding EC processes and how evolutionary algorithms can optimize and improve LLM architectures and their applications.
Topics of Interest
The combination of LLMs and Evolutionary Computing opens up new avenues for research that can push the boundaries of both fields. Potential topics of interest include, but are not limited to:
- Evolutionary Prompt Engineering: Applying evolutionary algorithm to develop effective prompts that maximize the utility of LLMs in various applications, such as text generation, question answering and summarization.
- LLM-Guided Evolutionary Algorithms: Incorporating LLMs into evolutionary algorithms as components that guide the search process, provide domain knowledge or generate candidate solutions.
- Co-evolution of LLMs and EC Techniques: Exploring the co-evolution of LLMs and EC techniques, where both evolve in tandem to solve complex, multi-modal or multi-objective problems.
- Benchmarking and Comparative Studies: Evaluating the performance of LLM- integrated evolutionary approaches against traditional EC methods across different optimization problems and domains.
- LLMs for Automated Code Generation in EC: Utilizing LLMs to automatically generate or refine code for evolutionary algorithms, potentially reducing the development time and improving the adaptability of EC methods.
- Optimization of LLM Architectures: Using evolutionary algorithms to optimize the hyperparameters, architecture and training processes of LLMs to enhance their performance on specific tasks.
- Applications in Real-World Problems: Demonstrating the application of LLM-EC hybrid approaches in real-world scenarios, such as optimization in engineering, healthcare, finance and creative industries.
Why Attend?
- Cutting-Edge Research: Be among the first to explore groundbreaking techniques at the intersection of these two powerful AI paradigms.
- Networking Opportunities: Connect with leading experts in both evolutionary computing and LLMs, fostering collaborations that push the boundaries of AI research.
- Practical Insights: Learn about real-world applications where LLMs and EC can enhance each other, providing actionable insights into how to leverage these technologies for your work.
Key Dates:
- Paper Submission Deadline: November 1, 2024 AoE
- Notification of Acceptance: TBA
- EvoStar 2025 Conference: April 23-25, 2025 in Trieste, Italy
Don’t miss out on this opportunity to be part of the conversation that’s shaping the future of AI! For more details, visit the EvoLLMs session page here.
Join us in Trieste and help define the next generation of AI systems!
Organisers
Niki van Stein, Thomas Bäck and Anna V. Kononova