Metraipolis › archive › dc_11679bdfb71e
When Should a World Model Move? Loss-Conditioned State Execution — arXiv:2609.15801
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.15801
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T22:48:07.484Z
- SHA-256 of the archived text
95952938ed6a1550582dd5b9b58cdd646773361f836da89edcd0287a99261be7- Stable URL of this page
https://metraipolis.com/documento/dc_11679bdfb71e
How to cite
When Should a World Model Move? Loss-Conditioned State Execution — arXiv:2609.15801 — arXiv (en), https://arxiv.org/abs/2609.15801 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_11679bdfb71e (Metraipolis archive dc_11679bdfb71e, sha256 95952938ed6a1550582dd5b9b58cdd646773361f836da89edcd0287a99261be7)
BibTeX
@misc{dc11679bdfb71e,
title = {When Should a World Model Move? Loss-Conditioned State Execution — arXiv:2609.15801},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.15801},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_11679bdfb71e; sha256 95952938ed6a1550582dd5b9b58cdd646773361f836da89edcd0287a99261be7},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.15801. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We introduce loss-conditioned state execution, a model-agnostic method that decides whether to execute a world model's fixed feasible proposal or retain the current state. Predictive informativeness alone, however, does not establish whether an update will reduce downstream loss. Occurrence ranking can approach perfection while persistence remains the unique absolute-loss Bayes action. Two transition laws can also share occurrence information and conditional variance yet require opposite absolute-loss decisions. We formalize state movability as the existence of a loss-reducing feasible correction and distinguish it from the benefit of a particular proposal. Our method constructs a loss-specific feasible proposal from a predictive distribution and evaluates its groupwise bounded-loss gain over persistence on independent calibration units. The proposal is executed only in groups with a positive simultaneous lower confidence bound. For fixed proposals and groups with bounded unit losses, we prove that every accepted group has lower expected loss than persistence with high probability when calibration units are i.i.d. draws from the target population. Experiments on public forecasting and action-conditioned dynamics benchmarks show supported updates and a trade-off between certification and coverage. On 28,684 held-out M4 Monthly series, the method executes the proposal for 14.0% of series and achieves bounded loss 0.588, compared with 0.599 for persistence and 0.621 for always executing the proposal. The paired 95% bootstrap intervals for both comparisons lie below zero. In constrained forecasting of six unhealthy-inventory types from JD$\mbox{.}$com, a leading e-retailer in China, strong occurrence-ranking signal coexists with a loss-based preference for persistence, illustrating why event predictability and state execution must be evaluated separately.
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); Optimization and Control (math.OC).
Pagina del lavoro: https://arxiv.org/abs/2609.15801 — 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 2026-10-15T22:29:03.365Z 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).