semantic-ingestion

Tag

Cards List
#semantic-ingestion

@yoheinakajima: i know it's backwards order, but experiment #2:

X AI KOLs Timeline · 2026-06-01 Cached

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.

0 favorites 0 likes
#semantic-ingestion

@yoheinakajima: longmemeval experiment arch: 1) deterministic ingestion/extraction (85.6% accuracy, 86.2% retrieval) 2) semantic ingest…

X AI KOLs Timeline · 2026-06-01 Cached

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.

0 favorites 0 likes
← Back to home

Submit Feedback