Machine Learning Algorithms & Natural Language Processing

Mar 14, 2026 · Artificial Intelligence

From Single to Multi-Granularity: How MemGAS Keeps Conversational Agents from Forgetting

The ICLR 2026 paper introduces MemGAS, a multi‑granularity memory framework that organizes dialogue history into session, turn, summary, and keyword levels, dynamically associates them with a Gaussian‑Mixture Model, selects the optimal granularity via entropy‑based routing, and achieves state‑of‑the‑art retrieval and QA performance on long‑term conversational benchmarks.