Metraipolis › archive › dc_641cfdc9496b

Recursive Organization Improvement: A Modeling Specification for Human--Agent Organizations — arXiv:2609.38643

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.38643
License (as archived): CC0-1.0
Archived: 2026-10-07T12:39:31.645Z
SHA-256 of the archived text: efe70c8eb6d52b1d4d371368bf406d8b0ba3fc049aaddb180a19b2f481e84234
Stable URL of this page: https://metraipolis.com/documento/dc_641cfdc9496b

How to cite

Recursive Organization Improvement: A Modeling Specification for Human--Agent Organizations — arXiv:2609.38643 — arXiv (en), https://arxiv.org/abs/2609.38643 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_641cfdc9496b (Metraipolis archive dc_641cfdc9496b, sha256 efe70c8eb6d52b1d4d371368bf406d8b0ba3fc049aaddb180a19b2f481e84234)

BibTeX

@misc{dc641cfdc9496b,
  title = {Recursive Organization Improvement: A Modeling Specification for Human--Agent Organizations — arXiv:2609.38643},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.38643},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_641cfdc9496b; sha256 efe70c8eb6d52b1d4d371368bf406d8b0ba3fc049aaddb180a19b2f481e84234},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.38643. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Stronger AI agents do not automatically produce better organizations: teams must also learn which work arrangements to retain and when to reconsider them. We propose a modeling specification for recursive organization improvement and evaluate it through an executable checker, a public-record mapping, and controlled simulation. The specification connects actor-visible histories, organizational memory, decision rights, and evidence-carrying change contracts. The mechanism study crosses six decision rules, three memory conditions, and three task environments under fixed resource ceilings. In a stationary environment, cumulative evidence raises balanced evaluation's normalized net value per task from 0.45224 to 0.48007. Repeated reassessment's disadvantage relative to this comparator falls from 0.01702 with reset evidence to 0.00007 with cumulative evidence. A reversal of the best workflow reveals the opposite cost: indefinite retention delays adaptation, while a finite window restores eventual performance at a transition cost. In exploratory controls, matching trial acquisition and label reuse reduces the apparent reassessment gain from 0.00607 to 0.00191. Program replacement adds no stable benefit across the tested reversal times. The study identifies evidence acquisition, reuse, and timely updating as mechanisms that must be separated from evaluator replacement when assessing organizational improvement.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-01 in cs.MA).
Categorie arXiv: Multiagent Systems (cs.MA) ; Human-Computer Interaction (cs.HC).
Pagina del lavoro: https://arxiv.org/abs/2609.38643 — 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 2026-10-07T12:12:18.623Z dalla pagina https://arxiv.org/catchup/cs.MA/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).