Jenny Zhang on Twitter / X

Hyperagents

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.

Harness Engineering for Self-Improvement

The concept of recursive self-improvement (RSI) dates back to I. J. Good (1965), where he defined an “ultraintelligent machine” as a system that can surpass humans in all intellectual activities and design better machines to improve itself. Yudkowsky (2008) used the phrase “recursive self-improvement” for a specific feedback loop: an AI uses its current intelligence to improve the cognitive machinery that produces its intelligence. This feedback loop in modern AI may indicate the model rewriting its own weights directly, or more broadly the model improves the training pipeline and the deployment system, which in turn enables a better successor model with improved performance across economically valuable tasks. The speed of research development in AI has been shown to drastically accelerated in frontier labs (Anthropic; OpenAI).

Import AI 455: AI systems are about to start building themselves.

The first step towards recursive self improvement

Prime Intellect - The Open Stack for Self-Improving Agents

The compute and infrastructure platform for you to train, evaluate, and deploy your own agentic models.

Prime Intellect - The Open Stack for Self-Improving Agents

The compute and infrastructure platform for you to train, evaluate, and deploy your own agentic models.

RSI Simulator: Play the Economics of Recursive Self-Improvement

Bootstrap an AI lab from scratch. A web game from Paradigm built on real economic models of AI recursive self-improvement.

AI agents team up in Agent Laboratory to speed scientific research

Johns Hopkins University and AMD have developed Agent Laboratory, a new open-source framework that pairs human creativity with AI-powered workflows.

When AI builds itself

Our progress toward recursive self-improvement, and its implications.

Meet Foundry: An AI Startup that Builds, Evaluates, and Improves AI Agents

Letta

Making machines that learn. Create stateful agents that remember everything, learn continuously, and improve themselves over time.

Introduction to Agents

Discover what actually works in AI. Join millions of builders, researchers, and labs evaluating agents, models, and frontier technology through crowdsourced benchmarks, competitions, and hackathons.

AI Was Made for RevOps

A new wave of GenAI and AI agents opens the door to faster, smarter, more scalable revenue teams—and higher revenue growth.

The Gap Through Which We Praise the Machine

My current theory of agentic programming: people are amazing at adapting the tools they're given and totally underestimate the extent to which they do it, and the amount of skill we build doing that is an incidental consequence of how badly the tools are designed.

Autoresearch: The feedback loop behind self-improving agents

Introspection co-founder Roland Gavrilescu explains autoresearch, agent “recipes,” self-improving loops, and why humans remain central to the software factory.

Lightcone Research

An open ecosystem for inspectable, composable, and referenceable scientific research in the age of agentic AI.