Metraipolis › archive › dc_b2115e2bcff6

Generalized Agent Iteration: One Formal Framework for Iterative Policy Improvement and Recursive Self-Improvement — arXiv:2609.13406

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.13406
License (as archived): CC0-1.0
Archived: 2026-10-15T22:46:26.778Z
SHA-256 of the archived text: 0f3679da9d7bbedfa989d3e5eb07cb43948df42b22009e7cfc3c466b2eb83f50
Stable URL of this page: https://metraipolis.com/documento/dc_b2115e2bcff6

How to cite

Generalized Agent Iteration: One Formal Framework for Iterative Policy Improvement and Recursive Self-Improvement — arXiv:2609.13406 — arXiv (en), https://arxiv.org/abs/2609.13406 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b2115e2bcff6 (Metraipolis archive dc_b2115e2bcff6, sha256 0f3679da9d7bbedfa989d3e5eb07cb43948df42b22009e7cfc3c466b2eb83f50)

BibTeX

@misc{dcb2115e2bcff6,
  title = {Generalized Agent Iteration: One Formal Framework for Iterative Policy Improvement and Recursive Self-Improvement — arXiv:2609.13406},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.13406},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b2115e2bcff6; sha256 0f3679da9d7bbedfa989d3e5eb07cb43948df42b22009e7cfc3c466b2eb83f50},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.13406. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

When we speak of recursive self-improvement (RSI), are we speaking of a phenomenon, a mechanism, or a prospect? Towards autonomous and evolving intelligence, RSI is being claimed at many scales, while no single framework that formally describes these emerging instances exists. Its counterpart in the classical realm, iterative policy improvement, is characterized by generalized policy iteration (GPI), a framework of broad applicability with well-understood theoretical properties, but only where the update principle and the evaluation base lie outside the agent. In this paper, we propose Generalized Agent Iteration (GAI), a formal framework that describes iterative policy improvement and RSI as two cases of a single learning paradigm. GAI defines the agent as a configuration of modifiable components within a system and models the learning process as a cycle of agent evaluation and agent improvement. Two pivotal dials then distinguish the instances: whether the improving mechanism is part of the agent and whether the standard it is measured against is grounded outside it. The former dial delineates the boundary between GPI and RSI, and the latter determines a system's polarity as anchored, goal drift, or fully self-referential. Moreover, we use these coordinates to place existing systems on the same two axes and make the defects of recursive self-improvement statable one condition at a time. We see this paper as a first step toward exploring a formal characterization of RSI that rests on the classical account, makes existing systems comparable, and provides a principled basis for analyzing and designing new ones.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-15 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.13406 — 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 2026-10-15T22:29:03.051Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).