Abstract:We critically examine the limitations of current AI models in achieving autonomous learning and propose a learning architecture inspired by human and animal cognition. The proposed framework integrates learning from observation (System A) and learning from active behavior (System B) while flexibly switching between these learning modes as a function of internally generated meta-control signals (System M). We discuss how this could be built by taking inspiration on how organisms adapt to real-world, dynamic environments across evolutionary and developmental timescales.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2603.15381 [cs.AI] |
| (or arXiv:2603.15381v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2603.15381 arXiv-issued DOI via DataCite |
Submission history
From: Emmanuel Dupoux [view email]
[v1]
Mon, 16 Mar 2026 14:54:56 UTC (2,827 KB)