发表机构
University at Albany, State University of New York（纽约州立大学奥尔巴尼分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究通过证据修订评估，比较了语言模型智能体在文档变更时修复记忆与重读证据的成本，发现源过滤重读在多数情况下更经济，且记忆修复效果未达显著优势。
AI 中文摘要
当支持智能体派生事实的文档被撤销或替换时，它应该修复记忆还是重读当前证据？我们引入了一个基于公共ICU记录中药物清单和问题清单任务的证据修订评估。在撤销、替换和对照事件下，我们比较了完整重读和源过滤重读，以及缓存、重建和图局部修复，使用了两个7B模型。记忆以完整形式提供，无需检索，成本包括摄取、修订和每次使用。在短记录上，局部修复使用的修订令牌比重建少5-10倍，但在保留条件下，每种记忆管道的成本至少是完整重读的两倍。在一个预先指定的小型开发扫描中，添加不符合任务条件的文档将记录扩展到约10,000个令牌；在该长度下，记忆的平均累积成本在2-14次使用后低于完整重读，部分通过截断提取实现，而源过滤重读仍然是最便宜的。在替换研究中，四个主要确认性测试均未达到统计显著性。这些结果表明，在证据修订后，智能体记忆的成本必须针对整个管道中的源过滤重读进行评估。
英文摘要
When documents supporting an agent's derived facts are revoked or replaced, should it repair memory or re-read current evidence? We introduce an evidence-revision evaluation on medication- and problem-list tasks from public ICU records. Under revocation, replacement and control events, we compare full and source-filtered re-reading with caching, rebuilding and graph-local repair across two 7B models. Memory is supplied in full without retrieval, and costs include ingest, revision and every use. On short records, local repair uses 5-10$\times$ fewer revision tokens than rebuilding, yet every memory pipeline costs at least twice full re-reading in held-out conditions. In a small pre-specified development sweep, adding task-ineligible documents extended records to about 10,000 tokens; at that length, memory's mean cumulative cost fell below full re-reading's after 2-14 uses, partly through truncated extraction, while source-filtered re-reading remained cheapest. In the replacement study, none of the four primary confirmatory tests reached statistical significance. These results show why the cost of agent memory after evidence revision must be assessed against source-filtered re-reading over the full pipeline.
Comments43 pages, 5 figures, 28 tables
