Exécution de notre outil de synthèse sur un nouvel article
Vérifiez l’article ci-dessous, puis lancez sa synthèse.
SegMem-RAG: Adaptive Memory for Retrieval-Augmented Generation in Open-Ended Knowledge Environments
Xuanbo Fan (Peking University), Tianqi Zhao, Yi Cheng, Chi Xiu, Jiaxin Guo (Peking University), Boci Peng (Peking University), Bingjing Xu, Jessica Zhang, Feng Sun, Yan Zhang (Peking University)
Résumé : 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.