Digital Red Queen: Adversarial Program Evolution in Core War with LLMs
Akarsh Kumar, Ryan Bahlous-Boldi, Prafull Sharma, Phillip Isola, Sebastian Risi, Yujin Tang, David Ha

TL;DR
This paper introduces Digital Red Queen, a self-play LLM-based evolution method in Core War that demonstrates continual adaptation, convergence towards general strategies, and potential applications in adversarial AI domains.
Contribution
It presents a novel Red Queen dynamics framework using LLMs to evolve adversarial programs in Core War, highlighting continual adaptation and convergence behaviors.
Findings
Warriors become more general over time
Warriors exhibit reduced behavioral diversity across runs
Red Queen dynamics enable continual adaptation
Abstract
Large language models (LLMs) are increasingly being used to evolve solutions to problems in many domains, in a process inspired by biological evolution. However, unlike biological evolution, most LLM-evolution frameworks are formulated as static optimization problems, overlooking the open-ended adversarial dynamics that characterize real-world evolutionary processes. Here, we study Digital Red Queen (DRQ), a simple self-play algorithm that embraces these so-called "Red Queen" dynamics via continual adaptation to a changing objective. DRQ uses an LLM to evolve assembly-like programs, called warriors, which compete against each other for control of a virtual machine in the game of Core War, a Turing-complete environment studied in artificial life and connected to cybersecurity. In each round of DRQ, the model evolves a new warrior to defeat all previous ones, producing a sequence of…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdversarial Robustness in Machine Learning · Machine Learning in Materials Science · Artificial Intelligence in Games
