Search papers, labs, and topics across Lattice.
This paper introduces PolyMemDB, a polyglot database system designed to enhance memory management for personal intelligent agents by addressing the limitations of existing memory systems. By employing a multi-storage architecture that accommodates diverse data types and incorporating a probabilistic inference engine, PolyMemDB effectively resolves long-term factual conflicts and reduces hallucinations in language models. The key result demonstrates that this approach significantly improves the accuracy and reliability of agent memory, providing users with personalized experiences while maintaining data provenance.
PolyMemDB resolves long-term factual conflicts in AI memory, drastically reducing hallucinations and enhancing user personalization.
With the widespread adoption of personal intelligent agents, users generate massive, heterogeneous data during long-term interactions. Leveraging this data as long-term memory helps reduce token overhead and deliver personalized experiences. However, existing memory systems face two primary limitations: they rely on single-storage paradigms that fragment multi-dimensional data, and they lack fine-grained data provenance to resolve long-term factual conflicts, thereby worsening LLM hallucinations. In this demonstration, we introduce PolyMemDB, a novel system tailored for managing agent memory. PolyMemDB has a polyglot storage architecture designed to track and manage various memory types, including graph, vector, probability and spatial-temporal data. To ensure factual consistency and reduce hallucinations, it features a probabilistic inference engine that integrates temporal decay with semiring aggregation, resolving long-term factual conflicts, providing detailed data provenance, and enabling users to trace reasoning chains transparently.
