长视野大型语言模型 (LLM) 代理依靠外部存储系统来在扩展交互中保留用户偏好和任务知识。传统检索机制优化语义兼容性，而不是下游实用程序, 经常将过时的, 误导, 或相互冲突的证据引入活动上下文中。我们提出了 MeClear, 一个任务条件内存清除框架，该框架通过合作归因识别具有负面下游效用的内存，并有选择地抑制它们执行代理。 MeClear 将留一筛选与采样合作 Shapley 归因相结合，在交互证据, 之间分配效用，有效解决单一去除评估失败的冗余冲突屏蔽问题。利用归因排名, MeClear 通过嵌套过滤, 执行查询范围的最小清除策略，验证已清除上下文上的任务恢复，而无需永久更改持久内存库。对十个长对话记忆池的综合实验评估表明，MeClear 实现了 85.9% 的目标召回率和 82.3%, 的总体任务恢复率，比留一 (LOO) 基线提高了 25.5 个百分点。
Long horizon Large Language Model (LLM) agents rely on external memory systems to preserve user preferences and task knowledge across extended interactions. Conventional retrieval mechanisms optimize semantic compatibility rather than downstream utility, frequently introducing outdated, misleading, or conflicting evidence into the active context. We present MeClear, a task conditioned memory clearance framework that identifies memories featuring negative downstream utility through cooperative attribution and selectively suppresses them from agent execution. MeClear combines Leave One Out screening with sampled cooperative Shapley attribution to distribute utility across interacting evidence, effectively resolving redundant conflict masking where single removal evaluations fail. Utilizing attribution rankings, MeClear executes a query scoped minimal clearance strategy over a nested filtration, verifying task recovery on the cleared context without permanently altering the persistent memory bank. Comprehensive experimental evaluations across ten long dialogue memory pools demonstrate that MeClear achieves a target recall of 85.9% and an overall task recovery rate of 82.3%, representing a 25.5 percentage point improvement over Leave One Out (LOO) baselines.
科目: 人工智能 (cs.AI); 软件工程 (cs.SE)
Subjects: Artificial Intelligence (cs.AI); Software Engineering (cs.SE)