ResearchTasksLong-horizon dialogue memory and conversational information trackingLong-horizon dialogue memory and conversational information trackingFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedLongMemEval 115K-token SInfoMem12.8LLM-as-Judge Accuracy4Jun 4, 2026