arXiv cs.AI
  • Score 83
  • Official

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

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 te

So what

What this event means by reading role—not a longer recap.

  • BuilderIf your agent prunes memory, validate query-critical false-drop risk on matched data or default to label-free retention instead of hard deletion.
  • ResearcherThe paper shows false-drop degrades accuracy more than false-keep, and global-accuracy crossovers are model- and task-specific diagnostics, not deployment thres

Score dimensions

Higher total means read first. Each bar is one factor we use to rank the system pool. How we score

RelevanceHow tightly this is about AI.
78
ImpactHow much this could change the field or the market.
55
NoveltyHow new this is versus a recap.
70
CredibilityHow much we trust the source.
92
ActionabilityWhether a reader can do something with it.
62