Lune

ACL Findings2026

MetaMem: Evolving Meta-Memory for Knowledge Utilization through Self-Reflective Symbolic Optimization

Haidong Xin, Xinze Li, Zhenghao Liu, Yukun Yan, Shuo Wang, Cheng Yang, Yu Gu, Ge Yu, Maosong Sun

Abstract

Existing memory systems enable Large Language Models (LLMs) to support long-horizon human-LLM interactions by persisting historical interactions beyond limited context windows. However, while recent approaches have succeeded in constructing effective memories, they often disrupt the inherent logical and temporal relationships within interaction sessions, resulting in fragmented memory units and degraded reasoning performance. In this paper, we propose MetaMem, a novel framework that augments memory systems with a self-evolving meta-memory, aiming to teach LLMs how to effectively utilize memorized knowledge. During meta-memory optimization, MetaMem iteratively distills transferable knowledge utilization experiences across different tasks by self-reflecting on reasoning processes and performing actions to update the current meta-memory state. The accumulated meta-memory units serve as explicit knowledge utilization experiences, guiding the LLM to systematically identify and integrate critical evidence from scattered memory fragments. Extensive experiments demonstrate the effectiveness of MetaMem, which significantly outperforms strong baselines by over 3.6%. All codes and datasets are available at https://github.com/OpenBMB/MetaMem.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • A-Mem: Agentic Memory for LLM Agents cites MemoryBank: Enhancing Large Language Models with Long-Term Memory
  • A-Mem: Agentic Memory for LLM Agents cites Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on10

  1. Retrieval-Augmented Generation for Knowledge-Intensive NLP TasksPatrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni et al.NeurIPS 2020 · 19,162 citations
  2. MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained TransformersWenhui Wang, Furu Wei, Li Dong, Hangbo Bao et al.NeurIPS 2020 · 2,727 citations
  3. Generative Agents: Interactive Simulacra of Human BehaviorJoon Sung Park, Joseph C. O'Brien, Carrie Jun Cai, Meredith Ringel Morris et al.UIST 2023 · 1,882 citations
  4. A-Mem: Agentic Memory for LLM AgentsWujiang Xu, Zujie Liang, Kai Mei, Hang Gao et al.NeurIPS 2025 · 1,138 citations
  5. MemoryBank: Enhancing Large Language Models with Long-Term MemoryWanjun Zhong, Lianghong Guo, Qiqi Gao, He Ye et al.AAAI 2024 · 394 citations

Related papers

  1. Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model AgentsYi Yu, Liuyi Yao, Yuexiang Xie, Qingquan Tan et al.ACL 2026 · 40 citations
  2. UMEM: Unified Memory Extraction and Management Framework for Generalizable MemoryYongshi Ye, Hui Jiang, Feihu Jiang, Tian Lan et al.ICML 2026 · 4 citations
  3. Beyond Meta-Reasoning: Metacognitive Consolidation for Self-Improving LLM ReasoningZiqing Zhuang, Linhai Zhang, Jiasheng Si, Deyu Zhou et al.ACL 2026
  4. MemWeaver: Weaving Hybrid Memories for Traceable Long-Horizon Agentic ReasoningJuexiang Ye, Xue Li, Xinyu Yang, Chengkai Huang et al.ACL Findings 2026
  5. Pre-Storage Reasoning for Episodic Memory: Shifting Inference Burden to Memory for Personalized DialogueSangyeop Kim, Yohan Lee, Sanghwa Kim, Hyunjong Kim et al.EMNLP Findings 2025 · 2 citations
Dusk over the sea between two cliffs drawn in fine vertical lines