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

arXiv: https://arxiv.org/abs/2604.27003 · HTML: https://mlsanity.com/paper/2604.27003/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Placed in Agent memory systems, one of 16 directions in LLM agents and tool use.
- Builds on 24 of its 31 references that are in the map.
- First posted on arXiv 29 Apr 2026.

## Placed in

- LLM agents and tool use / [Agent memory systems](https://mlsanity.com/agents/agent-memory-systems/)

## Builds on (most cited first, 24 of 24)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [Improving language models by retrieving from trillions of tokens](https://mlsanity.com/paper/2112.04426/) (2021)
- [ALFWorld: Aligning Text and Embodied Environments for Interactive Learning](https://mlsanity.com/paper/2010.03768/) (2020)
- [A-MEM: Agentic Memory for LLM Agents](https://mlsanity.com/paper/2502.12110/) (2025)
- [PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning](https://mlsanity.com/paper/1711.05769/) (2017)
- [ExpeL: LLM Agents Are Experiential Learners](https://mlsanity.com/paper/2308.10144/) (2023)
- [An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning](https://mlsanity.com/paper/2308.08747/) (2023)
- [A Survey on the Memory Mechanism of Large Language Model based Agents](https://mlsanity.com/paper/2404.13501/) (2024)
- [BabyAI: A Platform to Study the Sample Efficiency of Grounded Language Learning](https://mlsanity.com/paper/1810.08272/) (2018)
- [Synapse: Trajectory-as-Exemplar Prompting with Memory for Computer Control](https://mlsanity.com/paper/2306.07863/) (2023)
- [MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents](https://mlsanity.com/paper/2602.02474/) (2026)
- [AgentGym: Evolving Large Language Model-based Agents across Diverse Environments](https://mlsanity.com/paper/2406.04151/) (2024)
- [How Memory Management Impacts LLM Agents: An Empirical Study of Experience-Following Behavior](https://mlsanity.com/paper/2505.16067/) (2025)
- [CLIN: A Continually Learning Language Agent for Rapid Task Adaptation and Generalization](https://mlsanity.com/paper/2310.10134/) (2023)
- [Remember Me, Refine Me: A Dynamic Procedural Memory Framework for Experience-Driven Agent Evolution](https://mlsanity.com/paper/2512.10696/) (2025)
- [Skill Set Optimization: Reinforcing Language Model Behavior via Transferable Skills](https://mlsanity.com/paper/2402.03244/) (2024)
- [Continual Gradient Low-Rank Projection Fine-Tuning for LLMs](https://mlsanity.com/paper/2507.02503/) (2025)
- [Agent-Dice: Disentangling Knowledge Updates via Geometric Consensus for Agent Continual Learning](https://mlsanity.com/paper/2601.03641/) (2026)
- [SEE: Continual Fine-tuning with Sequential Ensemble of Experts](https://mlsanity.com/paper/2504.06664/) (2025)

## Built on by (most cited first, 10 of 10)

- [Forget to Improve: On-Device LLM-Agent Continual Learning via Budget-Curated Memory](https://mlsanity.com/paper/2606.25115/) (2026)
- [LatentGym: A Testbed For Cross-Task Experiential Learning With Controllable Latent Structure](https://mlsanity.com/paper/2606.15306/) (2026)
- [A Symbolic Neural CPU for Quantization-Simulated Writeback and Interpretable Program Execution](https://mlsanity.com/paper/2607.10021/) (2026)
- [What Makes Agent Memory Useful for Reliable Unanswerable Question Handling?](https://mlsanity.com/paper/2608.27924/) (2026)
- [Towards a Systems Foundation for Agentic Skills: Architecture, Lifecycle, and Security](https://mlsanity.com/paper/2608.29596/) (2026)
- [Continual Enterprise World Model Discovery in Dynamic Systems](https://mlsanity.com/paper/2609.19551/) (2026)
- [Beyond Skill Evolution: Self-Evolving Context Management Policies for Long-Horizon Agent Harnesses](https://mlsanity.com/paper/2609.34649/) (2026)
- [When Successful Memories Mislead Embodied Agents:Memory Adaption For Task-Conditioned Execution](https://mlsanity.com/paper/2609.35808/) (2026)
- [Beyond the Shadows of Plato's Cave: Evaluating False Memory in Autonomous Agents via Counterfactual Reasoning](https://mlsanity.com/paper/2609.39473/) (2026)
- [Beyond Outcome Feedback: Trajectory-Quality-Guided Experience-based Learning](https://mlsanity.com/paper/2610.14877/) (2026)

## Abstract (arXiv)

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.