从简单到专业：一个组合式可控图像描述智能体
From Simple to Professional: A Combinatorial Controllable Image Captioning Agent
AI总结：
本文提出 CapAgent，通过 MLLM 与检测、搜索等外部工具把简单用户指令转化为专业指令，并透明展示推理与工具调用，以生成符合多重约束的可控图像描述。
摘要：
Controllable Image Captioning Agent（CapAgent，可控图像描述智能体）是一个创新系统，旨在弥合图像描述任务中用户输入的简单性与专业级输出之间的差距。CapAgent 自动将用户提供的简单指令转换为详细、专业的指令，从而实现精确且具备情境感知能力的描述生成。通过利用多模态大语言模型（MLLM）以及目标检测工具和搜索引擎等外部工具，该系统确保生成的描述遵循指定准则，包括情感、关键词、关注点和格式。CapAgent 透明地控制描述过程的每一步，并在每一步展示其推理与工具使用情况，从而增强用户信任和参与度。项目代码可在 https://github.com/xin-ran-w/CapAgent 获取。
英文摘要：
The Controllable Image Captioning Agent (CapAgent) is an innovative system designed to bridge the gap between user simplicity and professional-level outputs in image captioning tasks. CapAgent automatically transforms user-provided simple instructions into detailed, professional instructions, enabling precise and context-aware caption generation. By leveraging multimodal large language models (MLLMs) and external tools such as object detection tool and search engines, the system ensures that captions adhere to specified guidelines, including sentiment, keywords, focus, and formatting. CapAgent transparently controls each step of the captioning process, and showcases its reasoning and tool usage at every step, fostering user trust and engagement. The project code is available at https://github.com/xin-ran-w/CapAgent.
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。
