跳到正文
arXiv cs.AI· Hongbin Lin, Sizhe Zou, Juangui Xu, Xinyue Xu, Zhuoli Ouyang, Stanislav Kolchin, Chengwei Qin, Zhongxiang Dai, Yao Shu·· 2 小时前AI 评分44

DR-BOLT:面向 VLM 自适应推理的双参考离线优化方法

Learning When to Think: Dual-Reference Offline Optimization for Adaptive VLM Reasoning

AI 导读

论文提出 DR-BOLT(Dual-Reference BOLT),通过双参考离线优化让视觉语言模型按输入难度自适应选择快思考或慢思考,避免强制长推理导致的过度思考。

正文 · 原文

View PDF HTML (experimental)

Abstract:Reasoning traces improve vision-language models on complex multimodal tasks, but forcing every input to follow a long reasoning process leads to overthinking and unnecessary inference cost. We study adaptive fast/slow thinking for VLMs, where one model answers directly for simple inputs and reasons step by step when needed. Fast answers and slow traces often come from distinct behavior policies, making a single-reference offline objective misweight one mode. We propose DUAL-REFERENCE BOLT (DR-BOLT), which distinguishes the desired fast/slow mixture reference from the sampling distribution and corrects their mismatch in reward-weighted training. Fast/slow partition competition explains routing in the optimal target; an efficient source-wise correction approximates the exact objective when response formats are well separated. Matched Qwen3-VL comparisons use identical candidate banks to isolate the objective from slow-teacher quality. DR-BOLT improves score-length trade-offs over the evaluated offline and online baselines on ScienceQA and three held-out transfer benchmarks, with a 24.1% cross-benchmark slow ratio and a 2.90-fold end-to-end training speedup over reproduced GRPO. These results support adaptive reasoning in the studied two-reference setting, while broader robustness remains open. Our code is available at this https URL.
Comments: Accepted to NeurIPS 2026
Subjects: Artificial Intelligence (cs.AI)
Cite as: arXiv:2611.09154 [cs.AI]
  (or arXiv:2611.09154v2 [cs.AI] for this version)
  https://doi.org/10.48550/arXiv.2611.09154

arXiv-issued DOI via DataCite

Submission history

From: Sizhe Zou [view email]
[v1] Fri, 6 Nov 2026 08:35:20 UTC (1,305 KB)
[v2] Wed, 18 Nov 2026 09:04:18 UTC (1,305 KB)

来源:arXiv cs.AI · arxiv.org