paper-with-me

Papers

DeltaMem: Towards Agentic Memory Management via Reinforcement Learning

2026-04-02 · Qi Zhang, Shen Huang, Chu Liu, Shouqing Yang, Junbo Zhao, Haobo Wang, Pengjun Xie arxiv

Recent advances in persona-centric memory have revealed the powerful capability of multi-agent systems in managing persona memory, especially in conversational scenarios. However, these complex frameworks often suffer from information loss and are fragile across varying scenarios, resulting in suboptimal performance. In this paper, we propose DeltaMem, an agentic memory management system that formulates persona-centric memory management as an end-to-end task within a single-agent setting. To further improve the performance of our agentic memory manager, we draw inspiration from the evolution of human memory and synthesize a user-assistant dialogue dataset along with corresponding operation-level memory updating labels. Building on this, we introduce a novel Memory-based Levenshtein Distance to formalize the memory updating reward, and propose a tailored reinforcement learning framework to further enhance the management capabilities of DeltaMem. Extensive experiments show that both training-free and RL-trained DeltaMem outperform all product-level baselines across diverse long-term memory benchmarks, including LoCoMo, HaluMem, and PersonaMem.

📄 PDF Abstract BibTeX arXiv:2604.01560

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

DELTAMEM: Incremental Experience Memory for LLM Agents via Residual Trees

2026-06-02 · Haoran Tan, Zeyu Zhang, Zhicheng Cao, Rui Li 외 arxiv

Large Language Model (LLM)-based agents increasingly rely on memory to learn from experiences over continual interactions. However, storing experiences as independent, flat units leads to substantial redundancy and retri…

Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model Agents

2026-01-05 · Yi Yu, Liuyi Yao, Yuexiang Xie, Qingquan Tan 외 arxiv

Large language model (LLM) agents face fundamental limitations in long-horizon reasoning due to finite context windows, making effective memory management critical. Existing methods typically handle long-term memory (LTM…

Reinforcement Learning

Memory as Action: Autonomous Context Curation for Long-Horizon Agentic Tasks

2025-10-14 · Yuxiang Zhang, Jiangming Shu, Ye Ma, Xueyuan Lin 외 arxiv

Long-context Large Language Models, despite their expanded capacity, require careful working memory management to mitigate attention dilution during long-horizon tasks. Yet existing approaches rely on external mechanisms…

Reinforcement Learning

AtomMem : Learnable Dynamic Agentic Memory with Atomic Memory Operation

2026-01-13 · Yupeng Huo, Yaxi Lu, Zhong Zhang, Haotian Chen 외 arxiv

Equipping agents with memory is essential for solving real-world long-horizon problems. However, most existing agent memory mechanisms rely on static and hand-crafted workflows. This limits the performance and generaliza…

Reinforcement Learning

Dynamic Skill Lifecycle Management for Agentic Reinforcement Learning

2026-05-11 · Junhao Shen, Teng Zhang, Xiaoyan Zhao, Hong Cheng arxiv

Large language model agents increasingly rely on external skills to solve complex tasks, where skills act as modular units that extend their capabilities beyond what parametric memory alone supports. Existing methods ass…

Reinforcement Learning