arXiv cs.AI· Dingjie Song, Zhiling Yan, Yuxuan Zhang, Lichao Sun·· 2 天前AI 评分38
LEV：用循环决策模型实现快速与深度思考
LEV: Thinking Fast and Deep with Looped Decision Models
AI 导读
LEV 是一种通过循环重跑网络层而非生成 token 来加深推理的决策模型，基于以循环方式预训练的语言模型，每步循环后读取选项并联合训练所有步骤，使同一权重可在任意深度作答。
正文 · 原文
Abstract:Decision models answer typed questions about an input with one probability per option, computed in a single forward pass without generating text. Like the fast System 1 of dual-process theory, they answer at once, but their depth is fixed at training time, so they spend the same computation on easy and hard questions. Models that reason in generated text can think longer, but they pay for every extra step in decoded tokens. We present LEV, a decision model that thinks deeper by rerunning its layers in a loop instead of generating tokens. LEV builds on a language model pretrained as a loop, reads the options after every loop step and trains all steps jointly, so one checkpoint can answer at any depth. On three looped backbones, accuracy rises with depth on the same weights, mostly on hard questions, and a 2.6B LEV goes from 63.2% at depth one to 76.2% at depth four on JevBench. On-demand depth, set per question by a small stopper with a threshold fitted on unlabelled requests, saves 15% to 24% of the computation at a cost of under one accuracy point, level with or slightly above a fixed mix of depths. On a locked test set, the 1.4B and 3B models are 5.4 to 8.8 points more accurate than dense (non-looped) models and cascades of the same latency below 50 ms.
| Comments: | 28 pages. Code: this https URL |
| Subjects: | Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.20951 [cs.AI] |
| (or arXiv:2610.20951v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.20951 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Dingjie Song [view email]
[v1]
Wed, 14 Oct 2026 21:20:03 UTC (320 KB)
来源：arXiv cs.AI · arxiv.org