Agents
activegraph longmemeval experiment #1: https://x.com/ActiveGraphAI/status/2059106393433780292?s=20
activegraph longmemeval experiment #1: https://x.com/ActiveGraphAI/status/2059106393433780292?s=20 [technical blog post] “Evidence Compilation Before Semantic Memory: ActiveGraph on LongMemEval-S” ——
activegraph longmemeval experiment #1: https://x.com/ActiveGraphAI/status/2059106393433780292?s=20 [technical blog post] “Evidence Compilation Before Semantic Memory: ActiveGraph on LongMemEval-S” —— 🔍85.6% QA accuracy and 86.2% turn answer-in-context at 2,462 mean context tokens, with deterministic non-generative ingestion https://activegraph.ai/blog/evidence-compilation-bef…
Source: Yohei Nakajima (X) | 2026-06-01