Metraipolis › archive › dc_2014d643cdc2

Execution Before Memory: Diagnosing Memory Failures in Video World Models — arXiv:2610.23542

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.23542
License (as archived): CC0-1.0
Archived: 2026-10-19T08:44:07.353Z
SHA-256 of the archived text: 616a5ea3abc2aeb56280c478eaeb1e47dac46d54fd5e56079221d28528e37ef0
Stable URL of this page: https://metraipolis.com/documento/dc_2014d643cdc2

How to cite

Execution Before Memory: Diagnosing Memory Failures in Video World Models — arXiv:2610.23542 — arXiv (en), https://arxiv.org/abs/2610.23542 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2014d643cdc2 (Metraipolis archive dc_2014d643cdc2, sha256 616a5ea3abc2aeb56280c478eaeb1e47dac46d54fd5e56079221d28528e37ef0)

BibTeX

@misc{dc2014d643cdc2,
  title = {Execution Before Memory: Diagnosing Memory Failures in Video World Models — arXiv:2610.23542},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.23542},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2014d643cdc2; sha256 616a5ea3abc2aeb56280c478eaeb1e47dac46d54fd5e56079221d28528e37ef0},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.23542. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

A memory test for a video world model should say whether the scene was set, whether the asked change was carried out, and whether the last frame shows the result. Current tests fold these into one number, so a low score is easy to read as forgetting. When the change is not carried out, the hidden state transition cannot appear, so the test is not really a test of memory. We introduce MIST, an evaluation that separates the change from the memory it should leave behind. The model first sets the scene while the change stays hidden, and only later is asked to show it, with leakage before that point kept under control. This separation locates the bottleneck: the model sets the scene but does not carry out the instructed change. The same gap appears in general memory evaluations. On that basis we propose M3-Agent (Make the Missing Move), which recursively revises the details of the input instruction so that the model successfully carries out the requested instruction. Relative to the baseline, it more than triples the MIST reveal score. On the benchmarks, WRBench's score T rises by 26.1% and MBench-T's score U by 52.7%. The method meets the problem from the execution side: it shows what the frozen model can do once the move is stated, and it sets a stricter baseline.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2610.23542 — 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 2026-10-19T08:39:24.906Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).