可控记忆使用：长期人机交互中锚定与创新的平衡

摘要

随着基于大语言模型的智能体日益广泛地应用于长期交互场景，累积记忆对于实现个性化服务和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：完整引入相关历史信息会导致"记忆锚定"现象，使智能体受困于过往交互；而完全排除记忆则会造成信息利用不足和重要交互历史的丢失。我们研究发现，智能体对记忆的依赖程度可被建模为一种显式且用户可调控的维度。我们首先提出了记忆依赖度的行为度量指标，用以量化历史交互对当前输出的影响程度。继而提出可调控记忆智能体框架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能够持续超越传统提示法和刚性记忆掩码策略，实现更精细有效的控制。

English

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 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 Steerable Memory Agent, 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.

可控记忆使用：长期人机交互中锚定与创新的平衡

Controllable Memory Usage: Balancing Anchoring and Innovation in Long-Term Human-Agent Interaction

摘要

Support