AI RESEARCH
MemRouter: Memory-as-Embedding Routing for Long-Term Conversational Agents
arXiv CS.AI
•
ArXi:2605.00356v1 Announce Type: cross Long-term conversational agents must decide which turns to in external memory, yet recent systems rely on autoregressive LLM generation at every turn to make that decision. We present MemRouter, a write-side memory router that decouples memory admission from the downstream answer backbone and replaces per-turn memory-management decoding with an embedding-based routing policy.