Metraipolis › archive › dc_d41eb9c82445

Verification and Self-Improvement in Agentic AI: Foundations and Limits — arXiv:2610.10611

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.10611
License (as archived)
CC0-1.0
Archived
2026-10-09T05:47:09.595Z
SHA-256 of the archived text
7e1c2a4240877610a0b19cc2130d90c97208ba11d5719198633c44088fc90e7e
Stable URL of this page
https://metraipolis.com/documento/dc_d41eb9c82445

How to cite

Verification and Self-Improvement in Agentic AI: Foundations and Limits — arXiv:2610.10611 — arXiv (en), https://arxiv.org/abs/2610.10611 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d41eb9c82445 (Metraipolis archive dc_d41eb9c82445, sha256 7e1c2a4240877610a0b19cc2130d90c97208ba11d5719198633c44088fc90e7e)
BibTeX
@misc{dcd41eb9c82445,
  title = {Verification and Self-Improvement in Agentic AI: Foundations and Limits — arXiv:2610.10611},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.10611},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d41eb9c82445; sha256 7e1c2a4240877610a0b19cc2130d90c97208ba11d5719198633c44088fc90e7e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.10611. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Agentic AI systems can improve by searching longer, receiving additional support, or modifying how they propose and verify outputs. A performance score does not distinguish these mechanisms. We compare these changes through bounded verification with hidden terminal randomness. A stage specifies admissible transcripts, polynomial bounds, an alternating verification protocol, and a terminal checker. Its native reach uses default support; its closure frontier permits all support already admitted by the interface. Under a uniform pointwise probability gap and task-relative soundness, these are well-defined languages. We prove that independent majority amplification preserves both languages, whereas existential acceptance over random tapes can admit incorrect outputs. Exact verification is the zero-randomness case, with placement and completeness results. The randomized-verifier classes satisfy $\Sigma_k^{\mathrm{P}}\subseteq\Sigma_k^{\mathrm{RV}}\subseteq\Sigma_{k+1}^{\mathrm{P}}$; strict enlargement and depth separation require explicit complexity assumptions, while $\mathrm{BPP}=\mathrm{P}$ yields exact companions with the same frontiers. Representation analysis separates invariant acceptance from core-versus-support labels that can change under refactoring. For recursive self-improvement, uniformly bounded self-modification under a common sound interpreter and fixed verification protocol remains within the same verification class. A separate conditional-error budget controls false selection across adaptively chosen candidates. A quota-enforced XOR-synthesis family separates unbounded ratios of search success from changes in the accepted languages; exact and probabilistic audits check the resulting evidence requirements. The framework ties self-improvement claims to obligations on correctness, admissible evidence, verification resources, and selection error.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computational Complexity (cs.CC).
Pagina del lavoro: https://arxiv.org/abs/2610.10611 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-09T05:47:00.487Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).