EvoLLMs at EvoStar 2027
We are thrilled to announce the special session at EvoStar 2027: EvoLLMs: Integrating Evolutionary Computing with Large Language Models. This session explores how large language models (LLMs) and evolutionary computing (EC) can benefit each other: using evolutionary techniques to optimise, enhance or understand LLMs, and using LLMs to advance evolutionary computing.
Official website: https://www.evostar.org/2027/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
Potential topics of interest include, but are not limited to:
- Evolutionary Prompt Engineering: Applying evolutionary algorithms 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.
- Optimization of LLM Architectures and Training: Using evolutionary algorithms to optimize the hyperparameters, architecture and training processes of LLMs.
- Applications in Real-World Problems: Demonstrating the application of LLM-EC hybrid approaches in real-world scenarios, such as engineering, healthcare, finance and creative industries.
Key Dates
- Paper Submission Deadline: 1 November 2026
- Notification of Acceptance: 10 January 2027
- Camera-ready Submission: 24 January 2027
- EvoStar 2027 Conference: 31 March - 2 April 2027, Mainz, Germany
For more details, visit the EvoLLMs session page here.
Join us in Mainz and help define the next generation of AI systems!
Previous Editions
Acknowledgements
This event is made possible by the IEEE CIS Task Force on Generative AI for Evolutionary Computation (GenAI4EC).
Organizers:
Niki van Stein
Prof. Thomas Bäck
