发表机构
Mahindra University（马恒达大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对长对话智能体记忆随时间变化的问题，提出基于能量最小化状态转移的MINDSET记忆控制器，通过版本化模式管理对话，在LoCoMo和MemoryAgentBench上取得最优性能。
AI 中文摘要
长对话智能体已成为我们日常生活中的重要组成部分。它们必须记住很久以前说过的话，以便高效地帮助我们完成任务，而无需用户重复指令和上下文。然而，主要问题在于指令和上下文会随时间变化，因此智能体必须能够相应地适应。一个有用的记忆系统应同时保留当前状态和历史状态，区分过时信息与活跃知识，检索与查询相符的证据，并避免反复调用大型语言模型来重写先前的交互。我们提出了MINDSET，一种记忆控制器，它将对话存储为不可变的情节，并通过最小能量状态转移将其组织为带版本的模式。每个新到达的情节可能强化、取代、拆分或创建一个模式。转移决策在表示失真、矛盾、历史损伤、碎片化和内部不一致性之间进行权衡，而迟滞机制可防止孤立的矛盾过早地重写稳定的记忆。我们在可复现的850个问题样本（700个LoCoMo + 150个MemoryAgentBench）上，将MINDSET与5种记忆系统进行了评估。MINDSET在LoCoMo上取得了最高的答案F1值，同时在检索排名（Recall@8、MRR和nDCG@8）上显著优于第二好的方法LightMem（经Holm校正后p<0.01）。它在MemoryAgentBench上也取得了最高得分，尽管相对差异较小。消融实验表明，受控碎片化和模式感知分配是答案质量的最大贡献因素。此外，使用GLM-4.7和Gemma-4-31B进行的700个问题的跨模型评估支持了模型无关性。这些结果表明，长期记忆可以更好地作为受约束的状态管理来处理，而非持续总结。
英文摘要
Long conversational agents have become essential in our daily lives. They must remember what was said long back in order to help us efficiently complete a task without needing the user to repeat instructions and context repeatedly. However, the main issue is that instructions and context change over time and so the agents must be able to adapt accordingly. A useful memory system should preserve both current and historical states, distinguish stale information from active knowledge, retrieve evidence appropriate to the query and avoid repeatedly invoking a large language model to rewrite prior interactions. We introduce MINDSET, a memory controller that stores a conversation as immutable episodes and organizes them into versioned schemas through minimum-energy state transitions. Each incoming episode may reinforce, supersede, split or create a schema. The transition decision balances representation distortion, contradiction, historical damage, fragmentation and internal inconsistency, while hysteresis prevents isolated contradictions from prematurely rewriting stable memory. We evaluate MINDSET against 5 memory systems on a reproducible sample of 850 questions (700 LoCoMo + 150 MemoryAgentBench). MINDSET obtains the highest observed LoCoMo answer F1 while significantly improving retrieval ranking (Recall@8, MRR and nDCG@8) over the second best method LightMem (p<0.01 after Holm correction). It obtains the highest observed scores on MemoryAgentBench although the relative difference is low. Ablations identify controlled fragmentation and schema-aware assignment as the largest contributors to answer quality. Additionally, a 700-question cross-model evaluation with GLM-4.7 and Gemma-4-31B supported model independence. These results show that long-term memory can be better handled as constrained state management rather than continual summarization.
