Praxis-VLM：通过文本驱动的强化学习实现视觉接地决策
Praxis-VLM: Vision-Grounded Decision Making via Text-Driven Reinforcement Learning
AI总结：
针对视觉语言模型复杂决策推理能力不足的问题，提出Praxis-VLM，通过文本场景下的GRPO算法训练推理能力，可迁移至多模态视觉决策任务，性能优于监督微调且泛化性更强。
摘要：
视觉语言模型在各类任务中表现出色，但往往缺乏复杂决策所需的精细情境推理能力。本文研究表明，当视觉场景被文本描述替代时，视觉语言模型能取得出人意料的优异决策表现，这说明基础推理能力可通过语言有效习得。受此启发，我们提出Praxis-VLM——一种面向视觉接地决策的推理型视觉语言模型。该模型在文本场景中采用GRPO（组相对策略优化）算法来注入稳健的推理能力，模型在此过程中学习评估动作及其后果。这些纯文本习得的推理技能可成功迁移至带视觉输入的多模态推理中，大幅降低对稀缺的图文配对训练数据的依赖。在多个不同决策基准上的实验显示，Praxis-VLM性能显著优于标准监督微调方法，展现出更优的性能与泛化性。进一步分析证实，该模型会进行明确且有效的推理，这是其性能与适应性提升的核心支撑。
英文摘要：
Vision Language Models exhibit impressive performance for various tasks, yet they often lack the sophisticated situational reasoning required for complex decision-making. This paper shows that VLMs can achieve surprisingly strong decision-making performance when visual scenes are replaced by textual descriptions, suggesting foundational reasoning can be effectively learned from language. Motivated by this insight, we propose Praxis-VLM, a reasoning VLM for vision-grounded decision-making. Praxis-VLM employs the GRPO algorithm on textual scenarios to instill robust reasoning capabilities, where models learn to evaluate actions and their consequences. These reasoning skills, acquired purely from text, successfully transfer to multimodal inference with visual inputs, significantly reducing reliance on scarce paired image-text training data. Experiments across diverse decision-making benchmarks demonstrate that Praxis-VLM substantially outperforms standard supervised fine-tuning, exhibiting superior performance and generalizability. Further analysis confirms that our models engage in explicit and effective reasoning, underpinning their enhanced performance and adaptability.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
