Finally, a good paper testing if graph memory actually beats flat retrieval for long-term agents. (bookmark this one) Researchers extract ea…

Finally, a good paper testing if graph memory actually beats flat retrieval for long-term agents. (bookmark this one) Researchers extract each conversational turn into typed nodes and attributed edges, answer from a two-hop subgraph, and hold the candidate-generation budget fixed at five retrieval roots. On LongMemEval the graph gets token F1 0.42 against 0.47 for a flat vector baseline, and a paired bootstrap over 500 questions puts the gap at -0.050 (95% CI -0.085 to -0.016). The damage concentrates on questions that require recalling a specific prior assistant turn, where judged correctness falls from 0.911 to 0.607. Splitting a turn into entities discards the surface form those questions depend on. The forgetting module fares much better. One pruning pass over a persistent 27,021-node graph, scored on recency, access frequency, degree centrality and age, removes 9.8% of nodes and 9.5% of stored bytes with token F1 unchanged. Paper: https://arxiv.org/abs/2608.28978 Chat with Paper: https://academy.dair.ai/papers/selective-forgetting-a-graph-based-memory-framework-for-long-term-llm-agents-2608.28978

Related

• MemORAI: Memory Organization and Retrieval via Adaptive Graph Intelligence for LLM Conversational Agents
• GRAVITY: Architecture-Agnostic Structured Anchoring for Long-Horizon Conversational Memory
• GAAMA: Graph Augmented Associative Memory for Agents

Source: DAIR.AI (X) | 2026-09-02