作者位次 #6/13ACL 2026Poster· Natural Language Processing
M emory- R 1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning
Sikuan Yan · Xiufeng Yang · Zuchao Huang · Ercong Nie · Zifeng Ding · Zonggen Li · Xiaowen Ma · Jinhe Bi · Kristian Kersting · Jeff Z. Pan · Hinrich Schuetze · Volker Tresp · Yunpu Ma
摘要
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 externa...