Learning How and What to Memorize: Cognition-Inspired Two-Stage Optimization for Evolving Memory

• URL: http://arxiv.org/abs/2605.00702v1
• Date: Fri, 01 May 2026 14:45:20 GMT
• Title: Learning How and What to Memorize: Cognition-Inspired Two-Stage Optimization for Evolving Memory
• Abstract summary: Large language model (LLM) agents require long-term user memory for consistent personalization.<n>Existing memory systems mainly rely on static, hand-crafted update rules.<n>We introduce MemCoE, a cognition-inspired two-stage optimization framework that learns how memory should be organized and what information to update.
• Score: 53.8372503928207
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Large language model (LLM) agents require long-term user memory for consistent personalization, but limited context windows hinder tracking evolving preferences over long interactions. Existing memory systems mainly rely on static, hand-crafted update rules; although reinforcement learning (RL)-based agents learn memory updates, sparse outcome rewards provide weak supervision, resulting in unstable long-horizon optimization. Drawing on memory schema theory and the functional division between prefrontal regions and hippocampus regions, we introduce MemCoE, a cognition-inspired two-stage optimization framework that learns how memory should be organized and what information to update. In the first stage, we propose Memory Guideline Induction to optimize a global guideline via contrastive feedback interpreted as textual gradients; in the second stage, Guideline-Aligned Memory Policy Optimization uses the induced guideline to define structured process rewards and performs multi-turn RL to learn a guideline-following memory evolution policy. We evaluate on three personalization memory benchmarks, covering explicit/implicit preference and different sizes and noise, and observe consistent improvements over strong baselines with favorable robustness, transferability, and efficiency.

Related papers

• Memory-R2: Fair Credit Assignment for Long-Horizon Memory-Augmented LLM Agents [27.2861945963127]
  Memory-augmented LLM agents enable interactions that extend beyond finite context windows.<n>Training such agents with reinforcement learning in multi-session environments is challenging.<n>We introduce Memory-R2, a training framework for memory-augmented LLM agents.
  arXiv  Detail & Related papers  (2026-05-20T22:02:00Z)
• AMemGym: Interactive Memory Benchmarking for Assistants in Long-Horizon Conversations [61.6579785305668]
  AMemGym is an interactive environment enabling on-policy evaluation and optimization for memory-driven personalization.<n>Our framework provides a scalable, diagnostically rich environment for advancing memory capabilities in conversational agents.
  arXiv  Detail & Related papers  (2026-03-02T15:15:11Z)
• Choosing How to Remember: Adaptive Memory Structures for LLM Agents [43.27579458682491]
  Memory is critical for enabling large language model (LLM) based agents to maintain coherent behavior over long-horizon interactions.<n>We propose a unified framework, FluxMem, that enables adaptive memory organization for LLM agents.<n> Experiments on two long-horizon benchmarks, PERSONAMEM and LoCoMo, demonstrate that our method achieves average improvements of 9.18% and 6.14%.
  arXiv  Detail & Related papers  (2026-02-15T07:56:24Z)
• Mem-T: Densifying Rewards for Long-Horizon Memory Agents [23.19373149519922]
  We introduce Mem-T, an autonomous memory agent that interfaces with a lightweight hierarchical memory database to perform dynamic updates and multi-turn retrieval over streaming inputs.<n>We also propose MoT-GRPO, a tree-guided reinforcement learning framework that transforms sparse terminal feedback into dense, step-wise supervision via memory operation tree backpropagation and hindsight credit assignment.
  arXiv  Detail & Related papers  (2026-01-30T14:23:33Z)
• MetaMem: Evolving Meta-Memory for Knowledge Utilization through Self-Reflective Symbolic Optimization [57.17751568928966]
  We propose MetaMem, a framework that augments memory systems with a self-evolving meta-memory.<n>During meta-memory optimization, MetaMem iteratively distills transferable knowledge utilization experiences across different tasks.<n>Extensive experiments demonstrate the effectiveness of MetaMem, which significantly outperforms strong baselines by over 3.6%.
  arXiv  Detail & Related papers  (2026-01-27T04:46:23Z)
• Fine-Mem: Fine-Grained Feedback Alignment for Long-Horizon Memory Management [63.48041801851891]
  Fine-Mem is a unified framework designed for fine-grained feedback alignment.<n> Experiments on Memalpha and MemoryAgentBench demonstrate that Fine-Mem consistently outperforms strong baselines.
  arXiv  Detail & Related papers  (2026-01-13T11:06:17Z)
• Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model Agents [57.38404718635204]
  Large language model (LLM) agents face fundamental limitations in long-horizon reasoning due to finite context windows.<n>Existing methods typically handle long-term memory (LTM) and short-term memory (STM) as separate components.<n>We propose Agentic Memory (AgeMem), a unified framework that integrates LTM and STM management directly into the agent's policy.
  arXiv  Detail & Related papers  (2026-01-05T08:24:16Z)
• Mem-α: Learning Memory Construction via Reinforcement Learning [20.916677456417464]
  Large language model (LLM) agents are constrained by limited context windows.<n>Current memory-augmented agents depend on pre-defined instructions and tools for memory updates.<n>Mem-alpha is a reinforcement learning framework that trains agents to effectively manage complex memory systems.
  arXiv  Detail & Related papers  (2025-09-30T08:02:34Z)
• Stable Hadamard Memory: Revitalizing Memory-Augmented Agents for Reinforcement Learning [64.93848182403116]
  Current deep-learning memory models struggle in reinforcement learning environments that are partially observable and long-term. We introduce the Stable Hadamard Memory, a novel memory model for reinforcement learning agents. Our approach significantly outperforms state-of-the-art memory-based methods on challenging partially observable benchmarks.
  arXiv  Detail & Related papers  (2024-10-14T03:50:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.