AI RESEARCH

Proactive Memory for Ad-Hoc Recall over Streaming Dialogues

arXiv CS.AI

ArXi:2603.04885v2 Announce Type: replace Real-world dialogue usually unfolds as an infinite stream. It thus requires bounded-state memory mechanisms to operate within an infinite horizon. However, existing read-then-think memory is fundamentally misaligned with this setting, as it cannot ad-hoc memory recall while streams unfold. To explore this challenge, we