作者位次 #6/10ACL 2026Findings· Findings of ACL
M em PO : Self-Memory Policy Optimization for Long-Horizon Agents
Ruoran Li · Xinghua Zhang · Haiyang Yu · Shitong Duan · Xiang Li · Wenxin Xiang · Chonghua Liao · Xudong Guo · Yongbin Li · Jinli Suo
摘要
Long-horizon agents face the challenge of growing context size during interaction with environment, which degrades the performance and stability. Existing methods typically introduce the external memory module and look up the relevant information from the stored memory, which prevents the model i...