Get Started
Home
Topics
Search
Library
Research questionHow can long-term conversational QA agents retrieve and reason over temporally dispersed dialogue history?In long-running conversations, relevant information may be separated by large spans of dialogue and expressed in ways that make direct retrieval difficult. Treating history as passively stored facts can leave gaps between retrieved evidence and the reasoning needed to answer questions.
AI Agents
AI Memory
Information Retrieval
Natural Language Processing
Reasoning
Retrieval-Augmented Generation
Latest papersRecent research connected to this question, newest first.RuleMem: Active Rule Memory for Long-Term Conversational AgentsThe source addresses question-answering agents for long-term conversations and reports results on the LoCoMo and LongMemEval_s* benchmarks. It describes induced natural-language Horn clauses and their validation, but the supplied evidence is limited to the reported benchmark evaluation.research paper · Sep 3, 2026
Related questions
How can long-video QA organize multimodal memory to preserve temporal and cross-modal grounding under limited context?How can assistants remember and reason about how users sounded across long, multi-session conversations?How can personalized LLM agents retrieve time-valid memories of persistent and evolving user states?How can conversational agents retrieve the right memories when users rely on implicit conversational context?