When Should LLM Agents Forget? Memory Filtering Under Query-Critical Resolver Errors
Not provided in the abstract
Abstract
The paper discusses the impact of memory filtering in LLMs, particularly how deleting stale facts can lead to reduced accuracy due to the loss of query-critical information.
Reality Card
The study demonstrates that hard-filtering of memory can lead to significant accuracy losses when query-critical facts are incorrectly deleted, with a sensitivity intervention showing a performance range from +0.230 to -0.181 based on resolver reliability.
A simple deployment-matched gate achieved an accuracy of 0.655 compared to 0.641 for hard-drop and 0.662 for oracle selection.
The findings are model- and task-specific, and global-accuracy crossovers require gold labels, which may limit generalizability.
Paper to code
Verified implementation resources so builders can test the paper’s claims instead of stopping at the abstract.