Agents
[New Technical Blog Post] In our second longmemeval experiment, we introduce semantic ingestion into recall leveraging the ActiveGraph runti…
[New Technical Blog Post] In our second longmemeval experiment, we introduce semantic ingestion into recall leveraging the ActiveGraph runtime. We started from a 60.6% baseline and improved to 83.4%/8
[New Technical Blog Post] In our second longmemeval experiment, we introduce semantic ingestion into recall leveraging the ActiveGraph runtime. We started from a 60.6% baseline and improved to 83.4%/84.8% for flat/agentic retrieval with LLM ingestion. https://activegraph.ai/blog/semantic-memory-forgot-the-assistant
Source: Yohei Nakajima (X) | 2026-05-31