Dataconomy
  • News
    • Artificial Intelligence
    • Cybersecurity
    • DeFi & Blockchain
    • Finance
    • Gaming
    • Startups
    • Tech
  • Industry
  • Research
  • Resources
    • Articles
    • Guides
    • Case Studies
    • Glossary
    • Whitepapers
  • Newsletter
  • + More
    • Conversations
    • Events
    • About
      • About
      • Contact
      • Imprint
      • Legal & Privacy
      • Partner With Us
Subscribe
No Result
View All Result
  • AI
  • Tech
  • Cybersecurity
  • Finance
  • DeFi & Blockchain
  • Startups
  • Gaming
Dataconomy
  • News
    • Artificial Intelligence
    • Cybersecurity
    • DeFi & Blockchain
    • Finance
    • Gaming
    • Startups
    • Tech
  • Industry
  • Research
  • Resources
    • Articles
    • Guides
    • Case Studies
    • Glossary
    • Whitepapers
  • Newsletter
  • + More
    • Conversations
    • Events
    • About
      • About
      • Contact
      • Imprint
      • Legal & Privacy
      • Partner With Us
Subscribe
No Result
View All Result
Dataconomy
No Result
View All Result

MAGELLAN: The AI that teaches itself by predicting its own learning

To test MAGELLAN, researchers used an interactive AI environment called Little-Zoo, where an LLM agent had to learn various tasks—like recognizing objects, growing plants, and even interacting with animals

byKerem Gülen
February 12, 2025
in Research

Large Language Models (LLMs) are getting smarter, but there’s one big problem: they don’t know how to learn efficiently. MAGELLAN is a new AI framework that mimics human learning by predicting its own progress—allowing it to navigate massive goal spaces without getting stuck on what’s too easy or too hard.

Developed by researchers from Inria and MIT, including Loris Gaven, Thomas Carta, Clément Romac, Cédric Colas, Sylvain Lamprier, Olivier Sigaud, and Pierre-Yves Oudeyer, the study “MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces” introduces a framework that gives AI a metacognitive ability—essentially, the skill to predict how much it will improve by practicing a task. This lets AI prioritize learning goals in an open-ended way, much like humans do when tackling new skills.

AI doesn’t prioritize learning well

Traditional AI learning methods struggle in vast goal spaces. They either:

Stay Ahead of the Curve!

Don't miss out on the latest insights, trends, and analysis in the world of data, technology, and startups. Subscribe to our newsletter and get exclusive content delivered straight to your inbox.

  1. Waste time on tasks they’ve already mastered, making slow progress.
  2. Attempt goals that are too difficult, leading to repeated failures.
  3. Require human-defined goal categories, which is inefficient and doesn’t scale.

Humans, on the other hand, instinctively seek out challenges that stretch their abilities without being impossible. MAGELLAN brings this human-like approach to LLM training.

How MAGELLAN works: Predicting progress, not just performance

Most AI training systems either:

  • Measure past performance (which doesn’t help with new goals).
  • Use fixed difficulty ratings (which don’t adapt to changing abilities).

MAGELLAN takes a smarter route. It dynamically estimates how much an AI will improve on a goal if it practices it. This allows AI models to select learning tasks that maximize progress rather than just attempt things randomly.

The method works through a process called Absolute Learning Progress (ALP)—tracking how much an AI improves on a given task over time. Using ALP, MAGELLAN clusters goals into meaningful categories without human intervention, letting AI generalize across related skills.


LLM performance scores are inflated: A new method shows the truth


Teaching AI to learn like a human

To test MAGELLAN, researchers used an interactive AI environment called Little-Zoo, where an LLM agent had to learn various tasks—like recognizing objects, growing plants, and even interacting with animals.

The results were clear:

  • AI trained with MAGELLAN outperformed all other methods, mastering more tasks faster.
  • It generalized better, meaning it could tackle new, unseen challenges more effectively.
  • It didn’t require human-labeled goal categories, proving its scalability.

By contrast, traditional learning approaches either plateaued early or required expert-defined goal groupings, making them rigid and inefficient.

Why this matters

MAGELLAN’s biggest breakthrough is self-directed learning. Instead of relying on human engineers to select goals, the AI can autonomously determine what to learn next based on its own progress. This shifts AI from being passively trained to actively improving itself, making it a transformative approach across multiple fields.

AI assistants can teach themselves new skills by identifying areas where they struggle, enhancing their ability to adapt without human intervention. In robotics, machines can refine their abilities by focusing on tasks with the highest learning potential, leading to more efficient and capable autonomous systems. In education, AI tutors can adjust lessons in real-time, not just based on past performance but on predicted improvement, offering a more personalized learning experience.

MAGELLAN proves that AI can think about its own learning, making it vastly more efficient in open-ended environments. The next step might bee xpanding this method beyond text-based goals into fields like robotics, scientific discovery, and even human education.


Featured image credit: Kerem Gülen/Ideogram

Tags: AIFeaturedllm

Related Posts

Physicists build and verify a quantum lie detector for large systems

Physicists build and verify a quantum lie detector for large systems

October 8, 2025
Lab breakthrough turns single laser into dozens of data streams on one chip

Lab breakthrough turns single laser into dozens of data streams on one chip

October 8, 2025
Project Paraphrase shows AI can redesign toxins to evade security screening

Project Paraphrase shows AI can redesign toxins to evade security screening

October 8, 2025
AI is now the number one channel for data exfiltration in the enterprise

AI is now the number one channel for data exfiltration in the enterprise

October 8, 2025
Yubico survey: 62% of Gen Z engaged with phishing scams

Yubico survey: 62% of Gen Z engaged with phishing scams

October 6, 2025
High-resolution computer mice can listen to conversations through desk vibrations

High-resolution computer mice can listen to conversations through desk vibrations

October 6, 2025

LATEST NEWS

Microsoft delays Xbox Game Pass price increase for some existing subscribers

Google releases Gemini 2.5 Computer Use model for building UI agents

AI is now the number one channel for data exfiltration in the enterprise

Google expands its AI vibe-coding app Opal to 15 more countries

Google introduces CodeMender, an AI agent for code security

Megabonk once again proves you don’t need fancy graphics to become a hit

Dataconomy

COPYRIGHT © DATACONOMY MEDIA GMBH, ALL RIGHTS RESERVED.

  • About
  • Imprint
  • Contact
  • Legal & Privacy

Follow Us

  • News
    • Artificial Intelligence
    • Cybersecurity
    • DeFi & Blockchain
    • Finance
    • Gaming
    • Startups
    • Tech
  • Industry
  • Research
  • Resources
    • Articles
    • Guides
    • Case Studies
    • Glossary
    • Whitepapers
  • Newsletter
  • + More
    • Conversations
    • Events
    • About
      • About
      • Contact
      • Imprint
      • Legal & Privacy
      • Partner With Us
No Result
View All Result
Subscribe

This website uses cookies. By continuing to use this website you are giving consent to cookies being used. Visit our Privacy Policy.