Get Started
Home
Topics
Search
Library
Research questionHow can personalized LLM agents retrieve time-valid memories of persistent and evolving user states?Dialogue order may differ from when an event actually occurred, and storing facts only as isolated points can erase how states persist or evolve. This can give an agent context that is temporally invalid or inconsistent with the user's history.
AI Agents
AI Memory
Evaluation & Benchmarks
Natural Language Processing
Retrieval-Augmented Generation
Latest papersRecent research connected to this question, newest first.Beyond Dialogue Time: Temporal Semantic Memory for Personalized LLM AgentsThe source presents Temporal Semantic Memory, which builds a semantic timeline, consolidates continuous related information into durative memories, and uses temporal intent during retrieval. It reports results on LongMemEval and LoCoMo, including up to a 12.2% absolute accuracy improvement; deployment requirements and broader evidence limits are not specified.research paper · Sep 2, 2026
Related questions
How can personalized dialogue agents keep evolving user personas traceable to supporting events during retrieval?How can LLM agents extract useful long-term memories for unknown future tasks without storing hallucinated facts?How can memory-augmented LLM agents coordinate memory construction, retrieval, and repair over long-horizon interactions?How can long-term LLM agents reconcile evolving textual evidence across interactions?