Back to Home
arXiv AI··Papers & Tech

When Should LLM Agents Forget? Memory Filtering Under Query-Critical Resolver Errors

中文摘要

研究发现LLM代理若因解析错误误删关键内存事实,硬过滤机制会显著降低其准确率,揭示了自动内存管理的风险。

English Summary

Hard-filtering stale facts in LLM memory reduces accuracy when resolver errors delete critical information, highlighting risks in automated agent memory management.

Original Excerpt

arXiv:2611.17338v1 Announce Type: new Abstract: LLM memory systems often delete facts classified as stale. We show that this hard-filtering step can reduce downstream accuracy when resolver errors delete query-critical facts. Across three models, a controlled sensitivity intervention moves hard-drop from gains of +0.186 to +0.230 at perfect resolution to losses of -0.176 to -0.181 at the lowest tested reliability. Paired targeted interventions show that false-drop causes significantly greater degradation than false-keep, while a non-deleting baseline can still fail when incorrect labels steer generation. On a frozen 102/102 calibration/test split, a simple deployment-matched gate reaches 0.655 accuracy versus 0.641 for always hard-drop and 0.662 for test-informed oracle selection. Global-accuracy crossovers require gold labels and are model- and task-specific diagnostics, not deployment thresholds. Deletion should instead be treated as cost-sensitive: validate query-critical false-drop risk on matched data, or default to label-free retention when such validation is unavailable.