When Continual Learning Moves to Memory: A Study of Experience Reuse in LLM Agents

• URL: http://arxiv.org/abs/2604.27003v1
• Date: Wed, 29 Apr 2026 04:48:02 GMT
• Title: When Continual Learning Moves to Memory: A Study of Experience Reuse in LLM Agents
• Abstract summary: Memory-augmented LLM agents offer an appealing shortcut to continual learning.<n>We show that this challenge does not disappear but resurfaces at the memory level.
• Score: 25.09835238706609
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Memory-augmented LLM agents offer an appealing shortcut to continual learning: rather than updating model parameters, they accumulate experience in external memory, seemingly sidestepping the stability-plasticity dilemma of parametric learning. We show that this challenge does not disappear but resurfaces at the memory level. Under a limited context window, old and new experiences compete during retrieval, relocating the continual-learning bottleneck from parameter updates to memory access. To study this phenomenon, we introduce a (k,v) framework that disentangles two fundamental design axes of external memory: how experience is represented and how it is organized for retrieval. Across sequential-task experiments in ALFWorld and BabyAI, we find that abstract procedural memories transfer more reliably than detailed trajectories, while negative transfer disproportionately harms the hard cases. Moreover, finer-grained memory organization is not universally beneficial: designs that yield strong forward transfer can simultaneously induce severe forgetting. Together, these results reveal that external memory does not resolve the continual-learning problem; it reshapes it into a problem of memory representation and retrieval design.

Related papers

• Dual-Layer Agentic Memory with Fast Write Routing and Slow Consolidation [27.410703803632718]
  We propose a framework that shifts memory management to the write phase through cost-aware routing and periodic parametric consolidation.<n>A 1.7B/8B cascade prunes up to 68% of redundant external memory while escalating fewer than 50% of inputs.<n>We further show that periodic consolidation successfully internalizes external knowledge, allowing the router to adaptively suppress redundant writes as the model's boundaries evolve.
  arXiv  Detail & Related papers  (2026-08-23T04:40:13Z)
• Is One Score Enough? Rethinking the Evaluation of Sequentially Evolving LLM Memory [50.857546269660276]
  We introduce SeqMem-Eval, a diagnostic evaluation framework for sequentially evolving large language models (LLMs) memory.<n>Rather than focusing only on final performance, SeqMem-Eval evaluates how memory states evolve, generalize, consolidate experience, and retain useful information during sequential inference.
  arXiv  Detail & Related papers  (2026-05-14T20:15:22Z)
• MemEvoBench: Benchmarking Memory MisEvolution in LLM Agents [78.95081012334116]
  Large Language Models (LLMs) with persistent memory enhances interaction continuity and personalization but introduces new safety risks.<n> contaminated or biased memory accumulation can trigger abnormal agent behaviors.<n>MemeEvoBench is the first benchmark evaluating memory safety in LLM agents against adversarial memory injection, noisy tool outputs, and biased feedback.
  arXiv  Detail & Related papers  (2026-04-17T07:29:52Z)
• Memory Retention Is Not Enough to Master Memory Tasks in Reinforcement Learning [44.94110361062394]
  Decision-making in the real world depends on memory that is both stable and adaptive.<n>Existing Reinforcement Learning benchmarks and memory-augmented agents focus primarily on retention.<n>We introduce a benchmark that explicitly tests continual memory updating under partial observability.
  arXiv  Detail & Related papers  (2026-01-21T15:27:23Z)
• Agentic Learner with Grow-and-Refine Multimodal Semantic Memory [50.81667005063605]
  ViLoMem is a dual-stream memory framework that constructs compact, schema-based memory.<n>It encodes visual distraction patterns and logical reasoning errors, enabling MLLMs to learn from their successful and failed experiences.
  arXiv  Detail & Related papers  (2025-11-26T18:55:08Z)
• Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory [89.65731902036669]
  Evo-Memory is a streaming benchmark and framework for evaluating self-evolving memory in large language model (LLM) agents.<n>We evaluate over ten representative memory modules and evaluate them across 10 diverse multi-turn goal-oriented and single-turn reasoning and QA datasets.
  arXiv  Detail & Related papers  (2025-11-25T21:08:07Z)
• ArcMemo: Abstract Reasoning Composition with Lifelong LLM Memory [21.4675019810992]
  Concept-level memory is reusable, modular abstractions distilled from solution traces and stored in natural language.<n>We evaluate on ARC-AGI, a benchmark that stresses compositional generalization and abstract reasoning.<n>We find abstract concepts to be the most consistent memory design, outscoring the baseline at all tested inference compute scales.
  arXiv  Detail & Related papers  (2025-09-04T17:54:19Z)
• 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)
• How Memory Management Impacts LLM Agents: An Empirical Study of Experience-Following Behavior [65.70584076918679]
  Memory is a critical component in large language model (LLM)-based agents.<n>This paper studies how memory management choices impact the LLM agents' behavior, especially their long-term performance.
  arXiv  Detail & Related papers  (2025-05-21T22:35:01Z)
• Memorization and Knowledge Injection in Gated LLMs [8.305942415868042]
  Large Language Models (LLMs) currently struggle to sequentially add new memories and integrate new knowledge.<n>Memory Embedded in Gated LLMs (MEGa) injects event memories directly into the weights of LLMs.<n>During inference, a gating mechanism activates relevant memory weights by matching query embeddings to stored memory embeddings.
  arXiv  Detail & Related papers  (2025-04-30T00:28:32Z)
• 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)
• Saliency-Guided Hidden Associative Replay for Continual Learning [13.551181595881326]
  Continual Learning is a burgeoning domain in next-generation AI, focusing on training neural networks over a sequence of tasks akin to human learning. This paper presents the Saliency Guided Hidden Associative Replay for Continual Learning. This novel framework synergizes associative memory with replay-based strategies. SHARC primarily archives salient data segments via sparse memory encoding.
  arXiv  Detail & Related papers  (2023-10-06T15:54:12Z)

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.