SegMem-RAG: Adaptive Memory for Retrieval-Augmented Generation in Open-Ended Knowledge Environments

Retrieval-Augmented Generation (RAG) improves the factual accuracy of large language models by grounding responses in external content. However, most RAG systems assume access to static and well-organized corpora with fixed retrieval logic. In practice, real-world sources are heterogeneous and unlabeled, including user-uploaded documents, manuals, and datasets. Effective access in such settings requires adaptive and self-directed retrieval behavior. We present SegMem‑RAG, a memory-augmented RAG framework that learns to route queries across multiple unlabeled corpora based on experience. It incrementally updates a structured memory and uses self-reflection to guide retrieval over time without supervision. Experimental results demonstrate that SegMem‑RAG significantly outperforms recent baselines in generation quality on multi-corpus QA tasks.

Authors

• Xuanbo Fan School of Intelligence Science and Technology, Peking University State Key Laboratory of General Artificial Intelligence, Peking University, Beijing, China
• Tianqi Zhao Microsoft Corporation, Beijing, China
• Yi Cheng Zhejiang University
• Chi Xiu Microsoft Corporation, Beijing, China
• Jiaxin Guo
• Boci Peng School of Intelligence Science and Technology, Peking University, Beijing, China State Key Laboratory of General Artificial Intelligence, Peking University, Beijing, China
• Bingjing Xu Microsoft Corporation, Beijing, China
• Jessica Zhang Microsoft Corporation, Beijing, China
• Feng Sun Microsoft Corporation
• Yan Zhang

Keywords

No keywords are indexed for this paper.