Metraipolis › archive › dc_cee43cc6ef5e
Action-Consequence Alignment for Reliable Planning and Self-Improving in Latent World Models — arXiv:2610.04539
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.04539
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T05:24:37.389Z
- SHA-256 of the archived text
fd721993cb47f116342f96e20711188876f8a2a052cd298ab55197dcae5660c7- Stable URL of this page
https://metraipolis.com/documento/dc_cee43cc6ef5e
How to cite
Action-Consequence Alignment for Reliable Planning and Self-Improving in Latent World Models — arXiv:2610.04539 — arXiv, https://arxiv.org/abs/2610.04539 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cee43cc6ef5e (Metraipolis archive dc_cee43cc6ef5e, sha256 fd721993cb47f116342f96e20711188876f8a2a052cd298ab55197dcae5660c7)
BibTeX
@misc{dccee43cc6ef5e,
title = {Action-Consequence Alignment for Reliable Planning and Self-Improving in Latent World Models — arXiv:2610.04539},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.04539},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cee43cc6ef5e; sha256 fd721993cb47f116342f96e20711188876f8a2a052cd298ab55197dcae5660c7},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.04539. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Latent world models learn to predict observed transitions, yet low prediction error alone does not guarantee reliable planning. Inspired by self tickling experiments in neuroscience showing that disrupting motor sensory correspondence increases prediction mismatch, we examine whether learned world models preserve an analogous action consequence this http URL results show nearby alternatives can receive lower prediction errors despite producing physical outcomes farther from the recorded target. With that future treated as a goal, this reveals a concrete prediction planning mismatch: the model assigns a lower cost to an action that achieves the target less accurately. To mitigate this gap, we introduce Action Consequence Alignment (ACA), a training objective that complements forward prediction by penalizing the prediction error advantage of locally searched alternatives over factual actions without additional model components or environment interactions during training. The same principle can also guide additional data collection for self improvement. We demonstrate that across diverse environments and evaluation settings, ACA improves planning performance and reduces real goal error, while ACA guided data collection outperforms random local sampling. These results support action consequence alignment as a practical principle for bridging predictive learning and reliable planning. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.04539 — 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 2026-10-06T05:24:05.483Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).