Cover Image

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

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Hu, Qisheng, Long, Quanyu, Wang, Wenya
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

BOOST: Bootstrapping Strategy-Driven Reasoning Programs for Program-Guided Fact-Checking
by: Hu, Qisheng, et al.
Published: (2025)

Coordinating Search-Informed Reasoning and Reasoning-Guided Search in Claim Verification
by: Hu, Qisheng, et al.
Published: (2025)

MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents
by: Zhang, Haozhen, et al.
Published: (2026)

Self-Verification Dilemma: Experience-Driven Suppression of Overused Checking in LLM Reasoning
by: Long, Quanyu, et al.
Published: (2026)

Decomposition Dilemmas: Does Claim Decomposition Boost or Burden Fact-Checking Performance?
by: Hu, Qisheng, et al.
Published: (2024)

Learning Query-Aware Budget-Tier Routing for Runtime Agent Memory
by: Zhang, Haozhen, et al.
Published: (2026)

Learn to Memorize: Optimizing LLM-based Agents with Adaptive Memory Framework
by: Zhang, Zeyu, et al.
Published: (2025)

MemoryBench: A Benchmark for Memory and Continual Learning in LLM Systems
by: Ai, Qingyao, et al.
Published: (2025)

Internalizing Meta-Experience into Memory for Guided Reinforcement Learning in Large Language Models
by: Huang, Shiting, et al.
Published: (2026)

Modular Memory is the Key to Continual Learning Agents
by: Dorovatas, Vaggelis, et al.
Published: (2026)

FLEX: Continuous Agent Evolution via Forward Learning from Experience
by: Cai, Zhicheng, et al.
Published: (2025)

State Contamination in Memory-Augmented LLM Agents
by: Wang, Yian, et al.
Published: (2026)

Agentic Unlearning: When LLM Agent Meets Machine Unlearning
by: Wang, Bin, et al.
Published: (2026)

TSN-Affinity: Similarity-Driven Parameter Reuse for Continual Offline Reinforcement Learning
by: Żurek, Dominik, et al.
Published: (2026)

Choosing How to Remember: Adaptive Memory Structures for LLM Agents
by: Lu, Mingfei, et al.
Published: (2026)

When to Stop Reusing: Dynamic Gradient Gating for Sample-Efficient RLVR
by: Miao, Yuchun, et al.
Published: (2026)

MIRA: Memory-Integrated Reinforcement Learning Agent with Limited LLM Guidance
by: Nourzad, Narjes, et al.
Published: (2026)

MemoryGraft: Persistent Compromise of LLM Agents via Poisoned Experience Retrieval
by: Srivastava, Saksham Sahai, et al.
Published: (2025)

Metacognitive Reuse: Turning Recurring LLM Reasoning Into Concise Behaviors
by: Didolkar, Aniket, et al.
Published: (2025)

Continual Diffuser (CoD): Mastering Continual Offline Reinforcement Learning with Experience Rehearsal
by: Hu, Jifeng, et al.
Published: (2024)

R2R2: Robust Representation for Intensive Experience Reuse via Redundancy Reduction in Self-Predictive Learning
by: Song, Sanghyeob, et al.
Published: (2026)

Learning Hierarchical Procedural Memory for LLM Agents through Bayesian Selection and Contrastive Refinement
by: Forouzandeh, Saman, et al.
Published: (2025)

Just-In-Time Reinforcement Learning: Continual Learning in LLM Agents Without Gradient Updates
by: Li, Yibo, et al.
Published: (2026)

Experience-Evolving Multi-Turn Tool-Use Agent with Hybrid Episodic-Procedural Memory
by: Li, Sijia, et al.
Published: (2025)

Decocted Experience Improves Test-Time Inference in LLM Agents
by: Shen, Maohao, et al.
Published: (2026)

When Planning Fails Despite Correct Execution: On Epistemic Calibration for LLM-Based Multi-Agent Systems
by: Wang, Zehao, et al.
Published: (2026)

RelayCaching: Accelerating LLM Collaboration via Decoding KV Cache Reuse
by: Geng, Yingsheng, et al.
Published: (2026)

MemReward: Graph-Based Experience Memory for LLM Reward Prediction with Limited Labels
by: Luo, Tianyang, et al.
Published: (2026)

Enhancing LLM Agents for Code Generation with Possibility and Pass-rate Prioritized Experience Replay
by: Chen, Yuyang, et al.
Published: (2024)

SketchOGD: Memory-Efficient Continual Learning
by: Min, Youngjae, et al.
Published: (2023)

When Does Multi-Agent RL Improve LLM Workflows? Workflow, Scale, and Policy-Sharing Tradeoffs
by: Zeng, Yifan, et al.
Published: (2026)

When Can We Reuse a Calibration Set for Multiple Conformal Predictions?
by: Balinsky, A. A., et al.
Published: (2025)

Matrix-Space Reinforcement Learning for Reusing Local Transition Geometry
by: Zhang, Zuyuan, et al.
Published: (2026)

CoPS: Empowering LLM Agents with Provable Cross-Task Experience Sharing
by: Yang, Chen, et al.
Published: (2024)

Neuroscience-Inspired Memory Replay for Continual Learning: A Comparative Study of Predictive Coding and Backpropagation-Based Strategies
by: Nalagatla, Goutham, et al.
Published: (2025)

When Continue Learning Meets Multimodal Large Language Model: A Survey
by: Huo, Yukang, et al.
Published: (2025)

Memory-Statistics Tradeoff in Continual Learning with Structural Regularization
by: Li, Haoran, et al.
Published: (2025)

Information-Theoretic Dual Memory System for Continual Learning
by: Wu, RunQing, et al.
Published: (2025)

Tree Search for LLM Agent Reinforcement Learning
by: Ji, Yuxiang, et al.
Published: (2025)

Exploratory Memory-Augmented LLM Agent via Hybrid On- and Off-Policy Optimization
by: Liu, Zeyuan, et al.
Published: (2026)