AI & ML Paradigm Shift

Introduces Hyperagents: self-referential systems where the meta-level modification logic is itself an editable program.

March 23, 2026

Original Paper

Hyperagents

Jenny Zhang, Bingchen Zhao, Wannan Yang, Jakob Foerster, Jeff Clune, Minqi Jiang, Sam Devlin, Tatiana Shavrina

arXiv · 2603.19461

The Takeaway

Unlike standard self-improving systems that use fixed meta-rules, Hyperagents can improve their own mechanism for generating improvements. This removes the 'domain-specific' bottleneck for self-acceleration, potentially allowing progress on any computable task.

From the abstract

Self-improving AI systems aim to reduce reliance on human engineering by learning to improve their own learning and problem-solving processes. Existing approaches to self-improvement rely on fixed, handcrafted meta-level mechanisms, fundamentally limiting how fast such systems can improve. The Darwin Gödel Machine (DGM) demonstrates open-ended self-improvement in coding by repeatedly generating and evaluating self-modified variants. Because both evaluation and self-modification are coding tasks,