Metraipolis › archive › dc_eefbbfce655c

Mind the Execution Gap: Action-Semantic Mismatch in World-Model Control — arXiv:2610.06582

Source: arXiv
Original: https://arxiv.org/abs/2610.06582
License (as archived): CC0-1.0
Archived: 2026-10-06T05:25:40.257Z
SHA-256 of the archived text: 7210ab96f0d094d139fa1b038a7070738e1c39ad1552e78f50ea68857dd842ea
Stable URL of this page: https://metraipolis.com/documento/dc_eefbbfce655c

How to cite

Mind the Execution Gap: Action-Semantic Mismatch in World-Model Control — arXiv:2610.06582 — arXiv, https://arxiv.org/abs/2610.06582 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_eefbbfce655c (Metraipolis archive dc_eefbbfce655c, sha256 7210ab96f0d094d139fa1b038a7070738e1c39ad1552e78f50ea68857dd842ea)

BibTeX

@misc{dceefbbfce655c,
  title = {Mind the Execution Gap: Action-Semantic Mismatch in World-Model Control — arXiv:2610.06582},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.06582},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_eefbbfce655c; sha256 7210ab96f0d094d139fa1b038a7070738e1c39ad1552e78f50ea68857dd842ea},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.06582. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

World-model controllers rely on action-conditioned dynamics for prediction and planning, yet real control systems often execute commands asynchronously due to communication delay, packet loss, reordering, and actuator buffering. We study how asynchronous execution changes the action semantics assumed within world-model controllers, rather than treating it only as an external control disturbance. Through controlled interventions, we identify two architecture-dependent failure modes: planning-based controllers such as TD-MPC2 suffer from a future-action timeline mismatch between imagined and executed action sequences, while recurrent world models such as DreamerV3 can attribute observed transitions to commands that were not actually applied. Our analysis shows that TD-MPC2 requires the correct future action sequence during latent dynamics rollout, whereas DreamerV3 requires timely attribution of each transition to the action that generated it. Based on these findings, we introduce two lightweight execution-consistent interfaces, Future-Sequence for TD-MPC2 and Applied-Action Feedback for DreamerV3, that correct these mismatches without modifying the pretrained world models. Experiments across delays, packet loss, reordering, multiple control domains, measured network traces, and a process-separated asynchronous stack consistently support both diagnoses and the corresponding architecture-specific corrections.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL); Information Retrieval (cs.IR); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.06582 — 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 2026-10-06T05:24:05.697Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).