Hybrid memory boosts long-term dialogue agent accuracy
Long-Term Agent Memory through Complementary Curation and Consolidation
Artificial IntelligenceMultiagent Systems
Summary
Memory systems help AI assistants remember past conversations and facts to respond better over long chats. The authors designed a memory setup that mixes two types: one that stores specific events and another that keeps organized facts and relationships. They also created a way to keep this memory efficient over time. Their tests show this design works better than existing ones on two standard challenges.
What this means in practice
- •For chatbot developers: Build dialogue agents that recall past interactions more accurately to provide better user experiences over long conversations.$Commercial implications: Enables more reliable long-term memory in commercial chatbots, improving customer interactions and retention.
- •For customer support teams: Create support systems that remember previous customer issues and relationships during extended service interactions.
Authors
Abhishek Gupta, Dongge Han, Daniel Madrigal Diaz, Wei-Ning Chen, Mayukh Das, Victor Rühle, Saravan Rajmohan
Abstract
Long-horizon dialogue agents require effective memory systems to recall facts, events, and relationships from interaction histories. In this work, we propose a hybrid-memory architecture comprising episodic memories and structured relational memories and a consolidation mechanism which preserves efficiency. We conduct an empirical study across two benchmarks: LoCoMo and LongMemEval-S. Our experiments demonstrate that the two memory types are consistently complementary, combining both outperform state-of-the-art memory frameworks and achieves 90.2% accuracy on LoCoMo and 85.5% on LongMemEval-S.