Metraipolis › archive › dc_bc0a640c4981

SerenAI: State-transition system inspired by text-based world AI models — arXiv:2609.06647

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.06647
License (as archived)
CC0-1.0
Archived
2026-10-16T12:56:54.032Z
SHA-256 of the archived text
16f564d1f7ac72b8bd195d9c4cc840dfaea756ed3dcad4dcdf443b75476cdece
Stable URL of this page
https://metraipolis.com/documento/dc_bc0a640c4981

How to cite

SerenAI: State-transition system inspired by text-based world AI models — arXiv:2609.06647 — arXiv (en), https://arxiv.org/abs/2609.06647 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bc0a640c4981 (Metraipolis archive dc_bc0a640c4981, sha256 16f564d1f7ac72b8bd195d9c4cc840dfaea756ed3dcad4dcdf443b75476cdece)
BibTeX
@misc{dcbc0a640c4981,
  title = {SerenAI: State-transition system inspired by text-based world AI models — arXiv:2609.06647},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.06647},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bc0a640c4981; sha256 16f564d1f7ac72b8bd195d9c4cc840dfaea756ed3dcad4dcdf443b75476cdece},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.06647. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Although professional workflows leverage large language models widely, the interpretation for auditing unconstrained free-text generation is usually intractable if such generation demands legal, operational or financial workflow. We hereby demonstrate a text based system called SerenAI - inspired by world-models, it is a state transition system that outputs verifiable predictions rather than merely text: Provided with a description of the environment, state, and actions, the generated output contains 4 items: causal deltas that causally effect the given state, a next state that can logically follow from the given state and action, a validity reward, and a termination signal. For the released proto-model, we employ 2 steps of adaptation training, namely parameter efficient fine-tuning followed by verifier based RL over 50,000 exampled cause and effects in 12 environments spanning 10 reasoning domains. Compared to an initial internal evaluation of an 8B open-weight baseline, SerenAI increased JSON validity from 85.0% to 93.2%, schema validity from 55.0% to 84.0%, exact structured-output match from 0.0% to 41.5%, causal-delta exact match from 0.0% to 41.5%, resulting-state exact match from 0.0% to 42.0%, reward exact match from 1.0% to 80.5%, and termination exact match from 38.0% to 81.5%. These support the narrower claim that verifier-compatible adaptation can improve structured transition prediction. They do not yet establish legal-grade reliability. Accordingly, the paper also specifies a validation protocol for evidence-grounded legal workflows, calibration, human oversight, and sovereign on-premise deployment.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-09 in cs.CL).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2609.06647 — 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 2026-10-16T12:30:25.274Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).