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

2026-01-27

arXiv.org

AI Summary

This work addresses the degradation of logical and temporal coherence in long-term human–AI interactions caused by fragmented memory systems, which impairs reasoning performance. To mitigate this, the authors propose MetaMem, a novel framework that introduces, for the first time, a self-evolving meta-memory mechanism. This mechanism explicitly accumulates cross-task experience in knowledge utilization through self-reflective reasoning, symbolic optimization, and iterative updates, thereby guiding evidence integration while preserving the structural integrity of memory. Experimental results demonstrate that MetaMem significantly outperforms strong baselines across multiple tasks, achieving performance gains exceeding 3.6% and substantially enhancing large language models’ ability to efficiently leverage memorized knowledge.

Technology Category

• Search and Optimization: Metareasoning and Metaheuristics
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

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.

Problem

• memory fragmentation
• knowledge utilization
• reasoning performance
• temporal relationships
• logical coherence

Innovation

• meta-memory
• self-reflection
• knowledge utilization
• symbolic optimization
• memory evolution