Metraipolis › archive › dc_688fa8a8e6d1

Intern-Decision: Efficient Multimodal Decision Making with Autoregressive Masked Language Modeling — arXiv:2610.22131

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.22131
License (as archived)
CC0-1.0
Archived
2026-10-16T10:02:01.034Z
SHA-256 of the archived text
1f97c9a1fabbe3baa474266a590379fbc4e30e3e2ef0302f6074c09914b8a88d
Stable URL of this page
https://metraipolis.com/documento/dc_688fa8a8e6d1

How to cite

Intern-Decision: Efficient Multimodal Decision Making with Autoregressive Masked Language Modeling — arXiv:2610.22131 — arXiv (en), https://arxiv.org/abs/2610.22131 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_688fa8a8e6d1 (Metraipolis archive dc_688fa8a8e6d1, sha256 1f97c9a1fabbe3baa474266a590379fbc4e30e3e2ef0302f6074c09914b8a88d)
BibTeX
@misc{dc688fa8a8e6d1,
  title = {Intern-Decision: Efficient Multimodal Decision Making with Autoregressive Masked Language Modeling — arXiv:2610.22131},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.22131},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_688fa8a8e6d1; sha256 1f97c9a1fabbe3baa474266a590379fbc4e30e3e2ef0302f6074c09914b8a88d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.22131. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Interactive agents repeatedly choose among a finite set of actions, labels, or ordinal outcomes. Generating a free-form response for each choice adds latency and complicates the interface between a model and its environment. We present Intern-Decision, a family of 0.8B, 2B, and 4B multimodal decision models that return structured choices and candidate probabilities from text and optional images. Our autoregressive masked language modeling objective places one decision placeholder per field in a complete assistant JSON skeleton. Ground-truth symbols appear only in supervision, while all fields are evaluated in a single causal forward pass using the backbone's native language-model head. The 4B model achieves a 90.02% unweighted average accuracy across seven evaluation suites, compared with 88.74% for Jev v1.13.0. For a fixed 289-token request with three fields on one RTX 4090, mean latency is 44.16 ms for the 4B model and approximately 33--34 ms for the smaller models. On a separate 96-case known-distribution pilot, temperature scaling reduces expected multiclass Brier from 0.628 to 0.550 and expected calibration error from 0.213 to 0.089. A confidence-based handoff study on 111 public Jevbench-Hard items improves accuracy from 82/111 (73.87%) to 97/111 (87.39%) by routing 42 items to Atria-Dawn-Preview. We also describe qualitative game, visual interface, and browser demonstrations. These results support compact decision models as a practical component of larger agent systems.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2610.22131 — 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 2026-10-16T08:44:47.693Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).