MAGELLAN augments LLM agents with online metacognitive LP prediction via semantic generalization to scale curriculum learning in open-ended goal spaces.
General intelligence requires rethinking exploration
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.AI 2years
2025 2representative citing papers
citing papers explorer
-
MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces
MAGELLAN augments LLM agents with online metacognitive LP prediction via semantic generalization to scale curriculum learning in open-ended goal spaces.
- Safety Must Precede the Deployment of Open-Ended AI