Zenil, Hector. “On the Limits of Self-Improving in LLMs and Why AGI, ASI and the Singularity Are Not Near Without Symbolic Model Synthesis”. SuperIntelligence - Robotics - Safety & Alignment 2, no. 4 (January 19, 2026). Accessed May 19, 2026. https://s-rsa.com/index.php/agi/article/view/17159.