Work

From Organizational Knowledge to AI Agent Memory: Empirical Validation of the SECI Model on the LongMemEval Benchmark

Year: 2026
Type: preprint
Abstract: AI agent memory systems face a fundamental design question: should conversational history be stored verbatim or transformed into structured knowledge before retrieval? We propose that the SECI model of knowledge creation \citep{nonaka1995knowledge} provides empirically testable design principles for AI agent memory architecture. We adapt the four SECI phases to the AI agent context and evaluate structured extraction against raw storage baselines on LongMemEval \citep{wu2025longmemeval}. Across 500 questions spanning six memory task types, SECI-based extraction achieves 93.9% Recall@5 versus 92.1% for raw storage, both using the same embedding model and vector database. The dominant factor is embedding window truncation: the model processes 256 tokens maximum, while sessions average 10{,}000 characters. Raw storage loses approximately 90% of content at the embedding layer; extraction condenses sessions into representations that fit the window. Per-task analysis reveals extraction leads on four of six question types, while raw storage outperforms on knowledge-update questions. The empirical contribution is mechanistic: we identify embedding window truncation as a previously unreported confound in the long-term-memory retrieval literature and isolate the gain attributable to representation condensation alone, holding embedder, vector store, and retrieval depth fixed. Code and data are publicly available.
Language: English
Open Access status: green
OpenAlex ID: W7167607753
Cites: 32
Cited by:
Related to: 10