| title | HAGE: Harnessing Agentic Memory via RL-Driven Weighted Graph Evolution |
|---|---|
| authors | Dongming Jiang, Yi Li, Guanpeng Li, Qiannan Li, Bingzhe Li |
| date | 2026-05-11 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2605.09942 |
| upvotes | 14 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| primer | Memory for AI agents |
| abstract | Memory retrieval in agentic large language model (LLM) systems is often treated as a static lookup problem, relying on flat vector search or fixed binary relational graphs. However, fixed graph structures cannot capture the varying strength, confidence, and query-dependent relevance of relationships between events. In this paper, we propose HAGE, a weighted multi-relational memory framework that reconceptualizes retrieval as sequential, query-conditioned traversal over a unified relational memory graph. Memory is organized as relation-specific graph views over shared memory nodes, where each edge is associated with a trainable relation feature vector encoding multiple relational signals. Given a query, an LLM-based classifier identifies the relational intent, and a routing network dynamically modulates the corresponding dimensions of the edge embedding. Traversal scores are computed via a learned combination of semantic similarity and these query-conditioned edge representations. This allows memory traversal to prioritize high-utility relational paths while softly suppressing noisy or weakly relevant connections. Beyond adaptive traversal, HAGE further introduces a reinforcement learning-based training framework that jointly optimizes routing behavior and edge representations using downstream tasks. Finally, empirical results demonstrate improved long-horizon reasoning accuracy and a favorable accuracy-efficiency trade-off compared to state-of-the-art agentic memory systems. Our code is available at https://github.com/FredJiang0324/HAGE_MVPReview. |
cite
@misc{jiang2026hage,
title={HAGE: Harnessing Agentic Memory via RL-Driven Weighted Graph Evolution},
author={Dongming Jiang and Yi Li and Guanpeng Li and Qiannan Li and Bingzhe Li},
year={2026},
eprint={2605.09942},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2605.09942}
}