SegMem-RAG: Adaptive Memory for Retrieval-Augmented Generation in Open-Ended Knowledge Environments
Xuanbo Fan, Tianqi Zhao, Yi Cheng, Chi Xiu, Jiaxin Guo, Boci Peng, Bingjing Xu, Jessica Zhang
Abstract
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.
BibTeX
@inproceedings{aaai2026_segmemragadaptiv,
title = {SegMem-RAG: Adaptive Memory for Retrieval-Augmented Generation in Open-Ended Knowledge Environments},
author = {Xuanbo Fan and Tianqi Zhao and Yi Cheng and Chi Xiu and Jiaxin Guo and Boci Peng and Bingjing Xu and Jessica Zhang and Feng Sun and Yan Zhang},
booktitle = {AAAI 2026},
year = {2026}
}