Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhang, Jenny, Zhao, Bingchen, Yang, Wannan, Foerster, Jakob, Clune, Jeff, Jiang, Minqi, Devlin, Sam, Shavrina, Tatiana
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2603.19461
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866918398945918976
author Zhang, Jenny
Zhao, Bingchen
Yang, Wannan
Foerster, Jakob
Clune, Jeff
Jiang, Minqi
Devlin, Sam
Shavrina, Tatiana
author_facet Zhang, Jenny
Zhao, Bingchen
Yang, Wannan
Foerster, Jakob
Clune, Jeff
Jiang, Minqi
Devlin, Sam
Shavrina, Tatiana
contents 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, gains in coding ability can translate into gains in self-improvement ability. However, this alignment does not generally hold beyond coding domains. We introduce \textbf{hyperagents}, self-referential agents that integrate a task agent (which solves the target task) and a meta agent (which modifies itself and the task agent) into a single editable program. Crucially, the meta-level modification procedure is itself editable, enabling metacognitive self-modification, improving not only the task-solving behavior, but also the mechanism that generates future improvements. We instantiate this framework by extending DGM to create DGM-Hyperagents (DGM-H), eliminating the assumption of domain-specific alignment between task performance and self-modification skill to potentially support self-accelerating progress on any computable task. Across diverse domains, the DGM-H improves performance over time and outperforms baselines without self-improvement or open-ended exploration, as well as prior self-improving systems. Furthermore, the DGM-H improves the process by which it generates new agents (e.g., persistent memory, performance tracking), and these meta-level improvements transfer across domains and accumulate across runs. DGM-Hyperagents offer a glimpse of open-ended AI systems that do not merely search for better solutions, but continually improve their search for how to improve.
format Preprint
id arxiv_https___arxiv_org_abs_2603_19461
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Hyperagents
Zhang, Jenny
Zhao, Bingchen
Yang, Wannan
Foerster, Jakob
Clune, Jeff
Jiang, Minqi
Devlin, Sam
Shavrina, Tatiana
Artificial Intelligence
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, gains in coding ability can translate into gains in self-improvement ability. However, this alignment does not generally hold beyond coding domains. We introduce \textbf{hyperagents}, self-referential agents that integrate a task agent (which solves the target task) and a meta agent (which modifies itself and the task agent) into a single editable program. Crucially, the meta-level modification procedure is itself editable, enabling metacognitive self-modification, improving not only the task-solving behavior, but also the mechanism that generates future improvements. We instantiate this framework by extending DGM to create DGM-Hyperagents (DGM-H), eliminating the assumption of domain-specific alignment between task performance and self-modification skill to potentially support self-accelerating progress on any computable task. Across diverse domains, the DGM-H improves performance over time and outperforms baselines without self-improvement or open-ended exploration, as well as prior self-improving systems. Furthermore, the DGM-H improves the process by which it generates new agents (e.g., persistent memory, performance tracking), and these meta-level improvements transfer across domains and accumulate across runs. DGM-Hyperagents offer a glimpse of open-ended AI systems that do not merely search for better solutions, but continually improve their search for how to improve.
title Hyperagents
topic Artificial Intelligence
url https://arxiv.org/abs/2603.19461