An autonomous AI agent teaches itself to become the world's top expert on MaxSAT by analyzing 229 weighted MaxSAT instances from the 2024 MaxSAT Evaluation. It discovers novel strategies, finds better solutions, and iteratively refines its toolbox without human guidance.

Current AI models struggle with autonomous learning due to inherent limitations. A new learning architecture is proposed, inspired by human and animal cognition, which incorporates learning from observation and active behavior.