发表机构
Beihang University; East China Normal University（北京航空航天大学; 华东师范大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对持久化语言智能体面临事实更新与历史查询冲突的问题，提出无需训练的RD-Forget框架，通过分离存储与使用、查询条件化记忆视图及率失真约束，在保留历史的同时控制过时信息影响，实验验证其有效性。
AI 中文摘要
持久化语言智能体需要存储的经验以在时间上保持可用，而每个答案都需要适合特定问题的证据。一个被取代的事实可能误导当前状态的答案，但仍可能对历史查询至关重要。我们提出RD-Forget，一个无需训练的框架，将智能体存储的内容与其使用的内容分离开来。一个保留的源档案保存观察结果，一个查询条件化的记忆视图控制它们对当前答案的影响。一个冻结的语言模型策展人提取相关证据，将事实分组到语义槽中，并保留多跳推理所需的关系。同槽替换链接在当前状态上下文中抑制被取代的值，而意图感知检索使早期证据再次可用。一个率失真公式指导在记忆预算内构建答案时视图。实验涵盖对话记忆、知识更新、事实整合、长上下文推理以及在共享回答流程下的个性化。结果将准确答案与查询相关证据构建和对过时备选方案的控制联系起来。没有遗忘或查询条件化的配置具有最大的分数差距，而槽分组、历史访问和关系保留贡献互补功能。保留历史同时选择性控制其使用，为适应变化的事实和未来的问题提供了一种实用方法。
英文摘要
Persistent language agents need stored experience to remain available across time, while each answer requires evidence suited to a particular question. A superseded fact can mislead a current-state answer and still be essential for a historical query. We present RD-Forget, a training-free framework that separates what an agent stores from what it uses. A retained source archive preserves observations, and a query-conditioned memory view controls their influence on the current answer. A frozen language-model curator extracts relevant evidence, groups facts into semantic slots, and preserves the relations needed for multi-hop reasoning. Same-slot replacement links suppress superseded values in current-state contexts, while intent-aware retrieval makes earlier evidence eligible again. A rate-distortion formulation guides construction of the answer-time view within a memory budget. Experiments span conversational memory, knowledge updating, fact consolidation, long-context reasoning, and personalization under a shared answering pipeline. The results associate accurate answers with both query-relevant evidence construction and control over obsolete alternatives. Configurations without forgetting or query conditioning have the largest score deficits, while slot grouping, historical access, and relation preservation contribute complementary functions. Retaining history while selectively controlling its use offers a practical way to accommodate changing facts and future questions.
Comments8 pages, 3 figures, 3 tables
