论文

LogT:用逻辑链驱动的图像思考提升视觉搜索能力

LogT: Logically Think with Images for Visual Search

精选理由

这篇论文有意思的地方是反过来做:不堆 RL 算力,而是把 SFT 数据的逻辑质量做扎实。Qwen2.5-VL-7B 微调后只用原来 1/120 的 GPU 时间就超过了此前 SFT+RL 的最强结果。做视觉 Agent 或多模态训练的团队值得看他们的数据构造方法。

论文提出 LogT(Logically Think with Images),一个全自动 SFT 数据引擎,通过逻辑链引导的推理生成高质量的视觉搜索训练数据,包含有挑战性的视觉接地问题和结构化的工具调用轨迹。作者将研究重点从提升 RL 复杂度转向 SFT 数据质量,认为后者才是关键瓶颈。

正文

实验中,研究团队用 LogT 数据集微调 Qwen2.5-VL-7B 和 InternVL3.5-8B 两个基座模型,并在 7 个基准测试集上评估。基于 Qwen2.5-VL-7B 的 LogT-SFT 仅用 3.1 倍更少的数据和超过 120 倍更少的 GPU 小时,就超过了此前用 SFT 和 RL 训练的最优方法。在 LogT-SFT 之上再加一个无需工具特定设计的简单 RL 流程,模型比此前复杂 RL 方案高出 9.59 分。

除性能提升外,该模型的工具调用准确率和效率更高,推理轨迹更结构化、逻辑更一致。这对资源有限的开发者有直接参考价值:与其堆 RL 训练算力,不如先把 SFT 数据的逻辑质量做好。

原文 · arXiv cs.LG

LogT: Logically Think with Images for Visual Search

Thinking with images empowers vision-language models (VLMs) to use an external Zoom-in tool for fine-grained visual search. Recent works employ supervised fine-tuning (SFT) and reinforcement learning (RL) with tool-specific designs to enable such capabilities. However, achieving logical reasoning alongside accurate and efficient tool use remains a significant challenge. To address this, we shift the focus away from increasing RL complexity and instead identify SFT data quality as a key bottleneck. We then propose LogT (short for Logically Think with Images), a fully automated SFT data engine that explicitly enforces logic-chain-guided reasoning. LogT generates an SFT dataset featuring challenging, visually grounded questions and structured tool-use traces with human-like logic. We validate our approach by fine-tuning two base models, Qwen2.5-VL-7B and InternVL3.5-8B, on the dataset and evaluating them across seven benchmark test sets. We show that LogT-SFT based on Qwen2.5-VL-7B outperforms the state-of-the-art trained with both SFT and RL, despite using 3.1$\times$ less data and $>120\times$ fewer GPU hours. Furthermore, applying a simple RL recipe without tool-specific design on LogT-SFT yields a model that surpasses prior methods with complex RL setups by a substantial 9.59-point margin. In addition to strong performance gains, our model exhibits higher tool-use accuracy and efficiency, as well as more structured and logically consistent reasoning traces, directly validating the effectiveness of our approach.

产业坐标与信源核验

本条情报归属 AITOP「论文」核心栏目,重点聚焦中国 AI 产业与国产大模型生态。在跨区域产业观察坐标中,该动态直接关联「AI 开发者工具链、Coding Agent 与工程化实践」研究主线,反映出当前技术演进与商业落地的最新风向。涉及核心实体与技术议题包括:Qwen2.5-VL、InternVL3.5、视觉搜索、SFT,读者可通过下方标签进入对应专题页查阅历史脉络与关联对比。

信源核验说明:本文原始线索采编自「arXiv cs.LG」(@Yanjun Fu, Quanzeng You, Jiadong Guo, Yujie Lu, Sai Charitha Akula, Haiping Wu, Miao Liu, Sanghamitra Dutta, Lu Yuan),经 AITOP 多维评分管线结构化提炼。