Tag
In our second longmemeval experiment, we introduce semantic ingestion into recall leveraging the ActiveGraph runtime, improving retrieval from 60.6% to 83.4%/84.8% for flat/agentic retrieval with LLM ingestion.
The tweet shares results from LongMemEval experiments comparing deterministic and semantic ingestion/extraction methods, achieving up to 87.6% accuracy and 90.0% retrieval with a hybrid approach.