Skip to content

RPMem: Learning Long-Term Recurrent Parametric Memory Across Sessions for LLM Agents

Sep 2026 · arXiv.org · Vol abs/2609.23466 · 1 citation · ⚡ 1 influential · 51 references
Computer Science

TL;DR

RPMem is introduced, a two-stage architecture that compiles each session into a model-independent latent memory through forward computation and selectively integrates it with retained memory via a task-trained recurrent gate, establishing RPMem as a lifecycle-independent parametric memory framework that maintains evolving cross-session memory that remains reusable across backbone replacements.

Abstract

Long-running LLM agents require memory that persists and evolves across sessions. Text-based memory retrieves and reconstructs past interactions at every query, making long-horizon performance increasingly dependent on retrieval quality and contextual reasoning as histories grow. Parametric memory encodes experience directly into model computation, but existing approaches provide limited support for cross-session memory evolution. Their coupling to a specific backbone further restricts memory reuse after model replacement. We introduce RPMem, a two-stage architecture that compiles each session into a model-independent latent memory through forward computation and selectively integrates it with retained memory via a task-trained recurrent gate. The consolidated memory is then mapped to backbone-specific low-rank adaptation (LoRA) parameters, allowing the encoding capability to transfer when the backbone is replaced. Evaluation across three long-term memory benchmarks and five diverse backbones demonstrates broad generalization with near-constant update cost and memory footprint. With Qwen3-8B on PERMA, RPMem reaches 85.52%, outperforming the strongest parametric and text-based baselines by 5.32 and 12.98 percentage points, respectively. Ablations validate the complementary roles of session compilation and cross-session consolidation, while dynamics analyses reveal that the gate acquires task-specific memory integration strategies. These results establish RPMem as a lifecycle-independent parametric memory framework that maintains evolving cross-session memory that remains reusable across backbone replacements. Our implementation is available at https://github.com/Quark-Medical/rpmem/tree/main.

View source

Similar papers

GenMem: Generative Symbolic Memory for Self-Evolving Harness

GenMem is presented, which reformulates memory management as generative symbolic addressing, a multi-level discrete token tuple drawn from a Cartesian-product address space that factorizes a million-scale sparse memory space using fewer than one hundred discrete symbols.

Xin-Ke Jiang, Tao Feng, Wei-Xuan Xu et al. · 0 citations
#artificial intelligence Preprint Sep 2026

MemAgent: Learning to Manage Heterogeneous Memory Providers for LLM Agents

MemAgent, featuring a content-aware routing architecture and a training-data synthesis pipeline, is proposed, featuring a content-aware routing architecture and a training-data synthesis pipeline that improves average accuracy and outperforms every individual memory method across all three benchmarks.

Yong-Xian Wei, Yi-Lin Zhao, Run-Xi Cheng et al. · 0 citations

ActiveMem: Dynamic Latent Memory Trees for Long-Horizon Agents

ActiveMem is proposed, a hierarchical memory framework that recursively organizes agent experiences into dependency-aware latent execution trees while explicitly preserving execution transitions, enabling coherent reasoning-path retrieval conditioned on the current execution state.

Song-Li Wu, Jing-Yi Wang, Zhao-Cheng Du et al. · 5 citations
#artificial intelligence Preprint Oct 2026

AMBER: Training Long-Horizon Web Agents through Append-Only Memory

Modern language-model agents increasingly interact with external environments over long-horizon, multi-step trajectories, where the accumulated interaction history can quickly exceed practical context budgets. To ensure reliability, agents must maintain factual information over long horizons, remember execution errors...

Chinmay Savadikar, Zhao-Yu Zhang, Ming-Yu Zhao et al. · 0 citations

Related blog posts

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.