Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Wang, Xinyuan, Mao, Wenyu, Wu, Junkang, Wang, Xiang, He, Xiangnan
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2605.13486
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913123172089856
author Wang, Xinyuan
Mao, Wenyu
Wu, Junkang
Wang, Xiang
He, Xiangnan
author_facet Wang, Xinyuan
Mao, Wenyu
Wu, Junkang
Wang, Xiang
He, Xiangnan
contents Deep search has recently emerged as a promising paradigm for enabling agents to retrieve fine-grained historical information without heavy memory pre-managed. However, existing deep search agents for memory system repeat past error behaviors because they fail to learn from the prior high- and low-quality search trajectories. To address this limitation, we propose R^2-Mem, a reflective experience framework for memory search systems. In the offline stage, a Rubric-guided Evaluator scores low- and high-quality steps in historical trajectories, and a self-Reflection Learner distills the corresponding abstract experience. During the online inference, the retrieved experience will guide future search actions to avoid repeated mistakes and maintain high-quality behaviors. Extensive experiments demonstrate that R^2-Mem consistently improves both effectiveness and efficiency over strong baselines, improving F1 scores by up to 22.6%, while reducing token consumption by 12.9% and search iterations by 20.2%. These results verify that R^2-Mem provides a RL-free and low-cost solution for self-improving LLM agents.
format Preprint
id arxiv_https___arxiv_org_abs_2605_13486
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle R^2-Mem: Reflective Experience for Memory Search
Wang, Xinyuan
Mao, Wenyu
Wu, Junkang
Wang, Xiang
He, Xiangnan
Computation and Language
Deep search has recently emerged as a promising paradigm for enabling agents to retrieve fine-grained historical information without heavy memory pre-managed. However, existing deep search agents for memory system repeat past error behaviors because they fail to learn from the prior high- and low-quality search trajectories. To address this limitation, we propose R^2-Mem, a reflective experience framework for memory search systems. In the offline stage, a Rubric-guided Evaluator scores low- and high-quality steps in historical trajectories, and a self-Reflection Learner distills the corresponding abstract experience. During the online inference, the retrieved experience will guide future search actions to avoid repeated mistakes and maintain high-quality behaviors. Extensive experiments demonstrate that R^2-Mem consistently improves both effectiveness and efficiency over strong baselines, improving F1 scores by up to 22.6%, while reducing token consumption by 12.9% and search iterations by 20.2%. These results verify that R^2-Mem provides a RL-free and low-cost solution for self-improving LLM agents.
title R^2-Mem: Reflective Experience for Memory Search
topic Computation and Language
url https://arxiv.org/abs/2605.13486