As LLM-based agents are increasingly used in long-term interactions, cumulative memory is critical for enabling personalization and maintaining stylistic consistency. However, most existing systems adopt an ``all-or-nothing'' approach to memory usage: incorporating all relevant past information can lead to \textit{Memory Anchoring}, where the agent is trapped by past interactions, while excluding memory entirely results in under-utilization and the loss of important interaction history. We show that an agent's reliance on memory can be modeled as an explicit and user-controllable dimension. We first introduce a behavioral metric of memory dependence to quantify the influence of past interactions on current outputs. We then propose \textbf{Stee}rable \textbf{M}emory Agent, \texttt{SteeM}, a framework that allows users to dynamically regulate memory reliance, ranging from a fresh-start mode that promotes innovation to a high-fidelity mode that closely follows interaction history. Experiments across different scenarios demonstrate that our approach consistently outperforms conventional prompting and rigid memory masking strategies, yielding a more nuanced and effective control for personalized human-agent collaboration.

翻译：随着基于大语言模型的智能体日益应用于长期交互场景，累积记忆对于实现个性化与保持风格一致性至关重要。然而，现有系统大多采用"全有或全无"的记忆使用策略：若纳入全部相关历史信息，可能导致**记忆锚定**现象，即智能体被过往交互所束缚；而完全排除记忆则会造成信息利用不足与重要交互历史的丢失。本文论证了智能体对记忆的依赖可被建模为显式且用户可控的维度。我们首先引入记忆依赖性的行为度量指标，以量化历史交互对当前输出的影响。随后提出**可调控记忆智能体框架** \texttt{SteeM}，该框架允许用户动态调节记忆依赖程度——从促进创新的"全新启动"模式，到严格遵循交互历史的"高保真"模式。多场景实验表明，我们的方法在个性化人机协作中始终优于传统提示策略与刚性记忆掩蔽方案，实现了更精细且高效的控制。