提出可控记忆干扰框架，揭示记忆间相互作用如何影响智能体持续学习能力。
Controlled Memory Interference in Continual LLM Agents
- 构建可控记忆干扰框架，模拟不同记忆关系下的演化过程。
- 发现特定干扰会显著抑制更新灵活性，但几乎不提升稳定性。
- 适合研究持续学习中记忆冲突问题的开发者与研究员。
长期记忆使智能体能跨会话保持连续性、个性化行为并基于经验进化。然而，记忆演变不仅是信息累积：新经验可能强化、修正或干扰已有记忆状态。现有系统多关注记忆构建与相关性检索，但多个记忆可能同时相关，却在状态、时效性或权威性上存在差异。本文提出可控记忆干扰（CMI）框架，用于诊断和生成数据以研究记忆在不同关系下的演化。在受控记忆演进中，良性累积影响有限，而特定关系的干扰会显著抑制更新可塑性，且几乎不带来稳定性提升，或通过阻断目标记忆暴露，或破坏其下游使用。词汇检索与密集检索表现出不同的干扰路径，而污染攻击对更新权威性的敏感度高于对时间远近的依赖。除诊断外，CMI还能生成针对性示例，支持抗干扰记忆学习，提升有效更新与干扰记忆的区分能力，同时保持原始记忆任务性能。结果表明，记忆演化不仅受记忆规模影响，更受积累经验间的交互作用塑造。更广泛而言，记忆干扰是可靠持续智能体记忆系统的关键因素。
原文摘要 · Abstract (English)
Long-term memory enables AI agents to maintain continuity across sessions, personalize behavior, and evolve through accumulated experience. Yet memory evolution is not simply a process of storing more information: new experiences may reinforce, revise, or interfere with existing memory states. Existing systems mainly emphasize memory construction and relevance-based retrieval, but several memories may remain simultaneously relevant while differing in state, temporal validity, or authority. We introduce Controlled Memory Interference (CMI), a controlled diagnostic and data-generation framework for studying how agent memory evolves under different memory relationships. Across controlled memory evolution, benign accumulation has limited effects, whereas relationship-specific interference sharply suppresses update plasticity with little stability gain, either by blocking target-memory exposure or by disrupting its downstream use. Lexical and Dense retrieval exhibit distinct interference pathways, while poisoning is more sensitive to update-authority cues than to recency alone. Beyond diagnosis, CMI provides targeted examples for interference-aware memory learning, improving the distinction between valid updates and interference-inducing memories while preserving performance on original memory tasks. These findings show that memory evolution is shaped not only by memory scale, but also by interactions among accumulated experiences. More broadly, memory interference emerges as an important factor for reliable continual agent memory systems.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。