NeFut Logo NeFut
Admin Login

[CS.AI] Interactive Memory Learning for Long-Term Conversations

Published at: 2026-09-16 22:00 Last updated: 2026-09-18 00:46
#Machine Learning #LLM #Artificial Intelligence

Recent advances in large language models have markedly improved agents' ability to model long‑term conversations. Existing approaches largely follow a static heuristic paradigm: information is archived passively without adaptive valuation, so memory management cannot evolve with user needs. To overcome this, we introduce ICML (InteraCtive Memory Learning), a multi‑agent framework that turns memory from a passive store into a learnable, interactive policy.\ \ We first employ a session synthesis pipeline to generate expert data, enabling rapid test‑time adaptation in unseen scenarios. ICML then applies online reinforcement learning where:\

Original Source: https://arxiv.org/abs/2609.17088

[h] Back to Home