ForgetEval
A paper examining forgetting-related failures in agent memory configurations. It evaluates 13 memory configurations and finds that scores for leading memory systems drop significantly when test cases are written by authors other than the system developers.
Timeline (last 90 days)
According to ForgetEval (arXiv:2606.15903) research on 13 Agent memory configurations, failures in production environments are mainly forgetting-type failures, such as rotated credentials still being recommended and deleted records still surfacing.
According to the ForgetEval research, when leading memory systems were scored on test cases written by people other than the authors themselves, internal test scores of 63%-68% plummeted to 28%-33%.
All Facts (2)
According to ForgetEval (arXiv:2606.15903) research on 13 Agent memory configurations, failures in production environments are mainly forgetting-type failures, such as rotated credentials still being recommended and deleted records still surfacing.
50%UnverifiedAccording to the ForgetEval research, when leading memory systems were scored on test cases written by people other than the authors themselves, internal test scores of 63%-68% plummeted to 28%-33%.
50%