Abstract
Large vision-language models (VLMs) fine-tuned on specialized visual instruction-following data have exhibited impressive language reasoning capabilities across various scenarios. However, this fine-tuning paradigm may not be able to efficiently learn optimal decision-making agents in multi-step goal-directed tasks from interactive environments. To address this challenge, we propose an algorithmic framework that fine-tunes VLMs with reinforcement learning (RL). Specifically, our framework provides a task description and then prompts the VLM to generate chain-of-thought (CoT) reasoning, enabling the VLM to efficiently explore intermediate reasoning steps that lead to the final text-based action. Next, the open-ended text output is parsed into an executable action to interact with the environment to obtain goal-directed task rewards. Finally, our framework uses these task rewards to fine-tune the entire VLM with RL. Empirically, we demonstrate that our proposed framework enhances the decision-making capabilities of VLM agents across various tasks, enabling 7b models to outperform commercial models such as GPT4-V or Gemini. Furthermore, we find that CoT reasoning is a crucial component for performance improvement, as removing the CoT reasoning results in a significant decrease in the overall performance of our method.
Abstract (translated)
大视觉语言模型（VLMs）在专用视觉指令跟随数据上进行微调已经展示了令人印象深刻的语言推理能力。然而，这种微调范式可能无法有效地从交互环境中学习最优决策策略。为解决这个问题，我们提出了一个使用强化学习（RL）微调VLMs的算法框架。具体来说，我们的框架提供任务描述，然后提示VLM生成连锁推理（CoT）思维，使VLM能够高效探索导致最终文本基于行动的中间推理步骤。接下来，开放的文本输出被解析为可执行动作，以与环境交互以获得目标导向任务奖励。最后，我们的框架使用这些任务奖励对整个VLM进行微调。实验证明，我们提出的框架增强了VLM代理在不同任务中的决策能力，使得7b模型能够优于诸如GPT4-V或Gemini等商业模型。此外，我们发现，CoT推理是提高性能的关键组成部分，因为去除CoT推理会导致我们方法的整体性能显著下降。
URL
https://arxiv.org/abs/2405.10292
