arXiv:2606. 28639v2 Announce Type: replace-cross Abstract: We establish the mathematical limits of AGI safety in two forms: verifying a fixed system, and verifying that a certified safety property persists once the system self-modifies.
By Jose Pascual Gumbau Mezquita
arXiv:2608. 15147v1 Announce Type: new Abstract: Machine intelligence has conquered the symbolic world but stalled at the physical one.
By Jiang Jiang (Persagy Science and Technology Co., Beijing, China), Yifu Sun (Persagy Science and Technology Co., Beijing, China), Qi Shen (Persagy Science and Technology Co., Beijing, China)
arXiv:2606. 26057v1 Announce Type: cross Abstract: AI agents are granted access to tools, APIs, and other infrastructure, making them active principals in those systems.
By Seth Dobrin, {\L}ukasz Chmiel
arXiv:2606. 26406v1 Announce Type: cross Abstract: We propose a complete architectural blueprint for safe artificial general intelligence based on a closed reentry loop (D I cycle).
By A. S. Ushakov, Yu. N. Berdinsk
The paper proves that algorithmic safety verification for Turing‑complete, self‑modifying systems—whether fixed or recursively self‑improving—is fundamentally limited. Statistically, no verifier can be sound, complete, and tractable across unbounded domains, all finite configurations, or succinctly described finite environments, due to Rice’s, Gödel’s, Trakhtenbrot’s, coNP, and PSPACE barriers. Dynamically, even a single self‑modification step can render safety properties undecidable, and no total supervisory algorithm can guarantee correctness for all such transformations, though a monitor that raises alarms on violations remains feasible.
whyItMatters":"The results show that formal safety guarantees for recursive self‑improvement are unattainable, highlighting intrinsic verification barriers for advanced AI systems."
By Jose Pascual Gumbau Mezquita
arXiv:2605. 09045v2 Announce Type: replace Abstract: Agentic frameworks are the software layer through which AI agents act in the world.
By Royce Moon, Lav R. Varshney