arXiv cs.CL· Tong Zhu, Zhe Xu, Zefeng He, Yunkai Chai, Xuyang Hu, Dehong Zheng, Yun Luo, Yafu Li, Qi Zhang, Yu Cheng·· 2 天前AI 评分34
Intern-Decision：用自回归掩码语言建模实现高效多模态决策
Intern-Decision: Efficient Multimodal Decision Making with Autoregressive Masked Language Modeling
AI 导读
Intern-Decision 是一组 0.8B、2B、4B 多模态决策模型，可从文本和可选图像输出结构化选项及候选概率，其自回归掩码语言建模目标在每个字段放置一个决策占位符，全部字段在单次因果前向传播中完成评估。
正文 · 原文
Abstract: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.
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.22131 [cs.CL] |
| (or arXiv:2610.22131v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.22131 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Tong Zhu [view email]
[v1]
Thu, 15 Oct 2026 16:05:48 UTC (4,532 KB)
来源：arXiv cs.CL · arxiv.org