MAGMA: A Multi-Graph based Agentic Memory Architecture for AI Agents
By: Dongming Jiang , Yi Li , Guanpeng Li and more
Potential Business Impact:
Helps AI remember and reason better over time.
Memory-Augmented Generation (MAG) extends Large Language Models with external memory to support long-context reasoning, but existing approaches largely rely on semantic similarity over monolithic memory stores, entangling temporal, causal, and entity information. This design limits interpretability and alignment between query intent and retrieved evidence, leading to suboptimal reasoning accuracy. In this paper, we propose MAGMA, a multi-graph agentic memory architecture that represents each memory item across orthogonal semantic, temporal, causal, and entity graphs. MAGMA formulates retrieval as policy-guided traversal over these relational views, enabling query-adaptive selection and structured context construction. By decoupling memory representation from retrieval logic, MAGMA provides transparent reasoning paths and fine-grained control over retrieval. Experiments on LoCoMo and LongMemEval demonstrate that MAGMA consistently outperforms state-of-the-art agentic memory systems in long-horizon reasoning tasks.
Similar Papers
MMAG: Mixed Memory-Augmented Generation for Large Language Models Applications
Computation and Language
Gives AI better memory for longer chats.
MMAG: Mixed Memory-Augmented Generation for Large Language Models Applications
Computation and Language
Makes AI remember past talks and you better.
MAGMA-Edu: Multi-Agent Generative Multimodal Framework for Text-Diagram Educational Question Generation
Artificial Intelligence
Creates better math problems with accurate pictures.