Large Language Models (LLMs) have demonstrated impressive capabilities across a wide range of NLP tasks, but they remain fundamentally stateless, constrained by limited context windows that hinder long-horizon reasoning. Recent efforts to address this limitation often augment LLMs with an external memory bank, yet most existing pipelines are static and heuristic-driven, lacking a learned mechanism for deciding what to store, update, or retrieve. We present Memory-R1, a reinforcement learning (RL) framework that equips LLMs with the ability to actively manage and utilize external memory through two specialized agents: a Memory Manager that learns structured operations, including ADD, UPDATE, DELETE, and NOOP; and an Answer Agent that pre-selects and reasons over relevant entries. Both agents are fine-tuned with outcome-driven RL (PPO and GRPO), enabling adaptive memory management with minimal supervision. With only 152 training QA pairs, Memory-R1 outperforms strong baselines and generalizes across diverse question types, three benchmarks (LoCoMo, MSC, LongMemEval), and multiple model scales (3B-14B).
@article{arxiv.2508.19828,
title = {Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning},
author = {Sikuan Yan and Xiufeng Yang and Zuchao Huang and Ercong Nie and Zifeng Ding and Zonggen Li and Xiaowen Ma and Jinhe Bi and Kristian Kersting and Jeff Z. Pan and Hinrich Schütze and Volker Tresp and Yunpu Ma},
journal= {arXiv preprint arXiv:2508.19828},
year = {2026}
}