Mem-α: Learning Memory Construction via Reinforcement Learning

• URL: http://arxiv.org/abs/2509.25911v1
• Date: Tue, 30 Sep 2025 08:02:34 GMT
• Title: Mem-α: Learning Memory Construction via Reinforcement Learning
• Authors: Yu Wang, Ryuichi Takanobu, Zhiqi Liang, Yuzhen Mao, Yuanzhe Hu, Julian McAuley, Xiaojian Wu,
• Abstract summary: 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.
• Score: 20.916677456417464
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language model (LLM) agents are constrained by limited context windows, necessitating external memory systems for long-term information understanding. Current memory-augmented agents typically depend on pre-defined instructions and tools for memory updates. However, language models may lack the ability to determine which information to store, how to structure it, and when to update it, especially as memory systems become more complex. This results in suboptimal memory construction and information loss. To this end, we propose Mem-alpha, a reinforcement learning framework that trains agents to effectively manage complex memory systems through interaction and feedback. We also construct a specialized training dataset spanning diverse multi-turn interaction patterns paired with comprehensive evaluation questions designed to teach effective memory management. During training, agents process sequential information chunks, learn to extract and store relevant content, then update the memory system. The reward signal derives from downstream question-answering accuracy over the full interaction history, directly optimizing for memory construction. To illustrate the effectiveness of our training framework, we design a memory architecture comprising core, episodic, and semantic components, equipped with multiple tools for memory operations. Empirical evaluation demonstrates that Mem-alpha achieves significant improvements over existing memory-augmented agent baselines. Despite being trained exclusively on instances with a maximum length of 30k tokens, our agents exhibit remarkable generalization to sequences exceeding 400k tokens, over 13x the training length, highlighting the robustness of Mem-alpha.

Related papers

• Graph-based Agent Memory: Taxonomy, Techniques, and Applications [63.70340159016138]
  Memory emerges as the core module in the Large Language Model (LLM)-based agents for long-horizon complex tasks.<n>Among diverse paradigms, graph stands out as a powerful structure for agent memory due to the intrinsic capabilities to model relational dependencies.<n>This survey presents a comprehensive review of agent memory from the graph-based perspective.
  arXiv  Detail & Related papers  (2026-02-05T13:49:05Z)
• 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)
• The AI Hippocampus: How Far are We From Human Memory? [77.04745635827278]
  Implicit memory refers to the knowledge embedded within the internal parameters of pre-trained transformers.<n>Explicit memory involves external storage and retrieval components designed to augment model outputs with dynamic, queryable knowledge representations.<n>Agentic memory introduces persistent, temporally extended memory structures within autonomous agents.
  arXiv  Detail & Related papers  (2026-01-14T03:24:08Z)
• AtomMem : Learnable Dynamic Agentic Memory with Atomic Memory Operation [40.1709026042412]
  We propose AtomMem, which reframes memory management as a dynamic decision-making problem.<n>By combining supervised fine-tuning with reinforcement learning, AtomMem learns an autonomous, task-aligned policy to orchestrate memory behaviors.<n> Experimental results across 3 long-context benchmarks demonstrate that the trained AtomMem-8B consistently outperforms prior static-workflow memory methods.
  arXiv  Detail & Related papers  (2026-01-13T08:22:28Z)
• Evaluating Long-Term Memory for Long-Context Question Answering [100.1267054069757]
  We present a systematic evaluation of memory-augmented methods using LoCoMo, a benchmark of synthetic long-context dialogues annotated for question-answering tasks.<n>Our findings show that memory-augmented approaches reduce token usage by over 90% while maintaining competitive accuracy.
  arXiv  Detail & Related papers  (2025-10-27T18:03:50Z)
• CAM: A Constructivist View of Agentic Memory for LLM-Based Reading Comprehension [55.29309306566238]
  Current Large Language Models (LLMs) are confronted with overwhelming information volume when comprehending long-form documents.<n>This challenge raises the imperative of a cohesive memory module, which can elevate vanilla LLMs into autonomous reading agents.<n>We draw inspiration from Jean Piaget's Constructivist Theory, illuminating three traits of the agentic memory -- structured schemata, flexible assimilation, and dynamic accommodation.
  arXiv  Detail & Related papers  (2025-10-07T02:16:30Z)
• Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning [59.16831804985279]
  Large Language Models (LLMs) have demonstrated impressive capabilities across a wide range of NLP tasks, but they remain fundamentally stateless.<n>Recent efforts to address this limitation often augment LLMs with an external memory bank, yet most existing pipelines are static and learned.<n>We present Memory-R1, a reinforcement learning framework that equips LLMs with the ability to actively manage and utilize external memory.
  arXiv  Detail & Related papers  (2025-08-27T12:26:55Z)
• Multiple Memory Systems for Enhancing the Long-term Memory of Agent [9.43633399280987]
  Existing methods, such as MemoryBank and A-MEM, have poor quality of stored memory content.<n>We have designed a multiple memory system inspired by cognitive psychology theory.
  arXiv  Detail & Related papers  (2025-08-21T06:29:42Z)
• MemOS: A Memory OS for AI System [116.87568350346537]
  Large Language Models (LLMs) have become an essential infrastructure for Artificial General Intelligence (AGI)<n>Existing models mainly rely on static parameters and short-lived contextual states, limiting their ability to track user preferences or update knowledge over extended periods.<n>MemOS is a memory operating system that treats memory as a manageable system resource.
  arXiv  Detail & Related papers  (2025-07-04T17:21:46Z)
• A-MEM: Agentic Memory for LLM Agents [42.50876509391843]
  Large language model (LLM) agents require memory systems to leverage historical experiences.<n>Current memory systems enable basic storage and retrieval but lack sophisticated memory organization.<n>This paper proposes a novel agentic memory system for LLM agents that can dynamically organize memories in an agentic way.
  arXiv  Detail & Related papers  (2025-02-17T18:36:14Z)
• HMT: Hierarchical Memory Transformer for Efficient Long Context Language Processing [33.720656946186885]
  Hierarchical Memory Transformer (HMT) is a novel framework that facilitates a model's long-context processing ability.<n>HMT consistently improves the long-context processing ability of existing models.
  arXiv  Detail & Related papers  (2024-05-09T19:32:49Z)
• Think Before You Act: Decision Transformers with Working Memory [44.18926449252084]
  Decision Transformer-based decision-making agents have shown the ability to generalize across multiple tasks. We argue that this inefficiency stems from the forgetting phenomenon, in which a model memorizes its behaviors in parameters throughout training. We propose a working memory module to store, blend, and retrieve information for different downstream tasks.
  arXiv  Detail & Related papers  (2023-05-24T01:20:22Z)

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.