Selective Forgetting: A Graph-Based Memory Framework for Long-Term LLM Agents
The framework extracts each conversational turn into typed nodes and attributed edges, answers questions from a two-hop subgraph, and periodically prunes nodes that score low on a weighted combination of recency, access frequency, degree centrality, and age.
Theo Rusu, S. Khanzadeh, Manar H. Alalfi
· 2 citations
· ⚡1