发表机构
Chance AI（机遇人工智能公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究在相机优先视觉智能体中个人视觉记忆对工具选择等的影响，采用三层视觉记忆调节大语言模型工具调用循环，通过对800张图像与合成内存块实验发现，移除三层内存块会降低工具查询相关性和端到端效用。
AI 中文摘要
识别告知智能体图像中有什么，个人记忆影响接下来值得查找的内容。在相机优先设置中，用户只能发送图像，因此智能体必须形成查找。我们研究个人视觉记忆是否能改善智能体端的工具选择和工具参数，从而实现更符合用户需求的多工具查找。该设计采用三层个人视觉记忆（简介、短期焦点、观察结果），在每次轮次加载，以在相机优先输入下调节大语言模型工具调用循环，还包括冲突感知回写，旨在为后续捕获刷新用户模型。在与为受控消融构建的合成内存块配对的800张图像上，移除完整的三层内存块会使工具查询相关性绝对降低0.47分（在5分制上从4.21降至3.74；相对降低11.2%），端到端效用绝对降低0.082（从0.842降至0.760；相对降低9.7%）。这些结果衡量了在仅图像输入且有固定合成块的情况下工具策略的内存调节，而非来自实时用户历史记录的多会话回写。
英文摘要
Recognition tells an agent what is in an image; personal memory affects what is worth looking up next. In a camera-first setting the user can send only an image, so the agent must form the lookups. We study whether personal visual memory improves agent-side tool choice and tool arguments, and thereby more user-aligned multi-tool lookups. The design uses a three-layer personal visual memory (profile, short-term focus, observations) that is loaded on each turn to condition an LLM tool-calling loop under camera-first intake, and includes conflict-aware write-back intended to refresh the user model for later captures. On 800 images paired with synthetic memory blocks constructed for controlled ablation, removing the full three-layer memory block reduces tool-query relevance by 0.47 points absolute (4.21 -> 3.74 on a 5-point scale; 11.2% relative) and end-to-end utility by 0.082 absolute (0.842 -> 0.760; 9.7% relative). These results measure memory conditioning of tool policy under image-only intake with fixed synthetic blocks, not multi-session write-back from live user histories.
Comments13 pages, 3 figures, 4 tables. Equal contribution: Xiaofan Wu, Xi Zeng. Corresponding author: xiaofan@chance.vision
