[2603.01783] GAM-RAG: Gain-Adaptive Memory for Evolving Retrieval in Retrieval-Augmented Generation

Computer Science > Artificial Intelligence arXiv:2603.01783 (cs) [Submitted on 2 Mar 2026] Title:GAM-RAG: Gain-Adaptive Memory for Evolving Retrieval in Retrieval-Augmented Generation Authors:Yifan Wang, Mingxuan Jiang, Zhihao Sun, Yixin Cao, Yicun Liu, Keyang Chen, Guangnan Ye, Hongfeng Chai View a PDF of the paper titled GAM-RAG: Gain-Adaptive Memory for Evolving Retrieval in Retrieval-Augmented Generation, by Yifan Wang and 7 other authors View PDF HTML (experimental) Abstract:Retrieval-Augmented Generation (RAG) grounds large language models with external evidence, but many implementations rely on pre-built indices that remain static after construction. Related queries therefore repeat similar multi-hop traversal, increasing latency and compute. Motivated by schema-based learning in cognitive neuroscience, we propose GAM-RAG, a training-free framework that accumulates retrieval experience from recurring or related queries and updates retrieval memory over time. GAM-RAG builds a lightweight, relation-free hierarchical index whose links capture potential co-occurrence rather than fixed semantic relations. During inference, successful retrieval episodes provide sentence-level feedback, updating sentence memories so evidence useful for similar reasoning types becomes easier to activate later. To balance stability and adaptability under noisy feedback, we introduce an uncertainty-aware, Kalman-inspired gain rule that jointly updates memory states and perplexity-based uncert...