Cover Image

State Contamination in Memory-Augmented LLM Agents

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Yian, Goyal, Agam, Chen, Yuen, Sundaram, Hari
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

CausalDetox: Causal Head Selection and Intervention for Language Model Detoxification
by: Wang, Yian, et al.
Published: (2026)

On the Necessity of Output Distribution Reweighting for Effective Class Unlearning
by: Ebrahimpour-Boroojeny, Ali, et al.
Published: (2025)

DIVEBATCH: Accelerating Model Training Through Gradient-Diversity Aware Batch Size Adaptation
by: Chen, Yuen, et al.
Published: (2025)

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

MemGuard: Preventing Memory Contamination in Long-Term Memory-Augmented Large Language Models
by: Ha, Hyeonjeong, et al.
Published: (2026)

Toxic HallucinAItions: Perturbing Prompts and Tracing LLM Circuits
by: Shimgekar, Soorya Ram, et al.
Published: (2026)

RAP: Retrieval-Augmented Planning with Contextual Memory for Multimodal LLM Agents
by: Kagaya, Tomoyuki, et al.
Published: (2024)

FOAM: Blocked State Folding for Memory-Efficient LLM Training
by: Wen, Ziqing, et al.
Published: (2025)

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

KernelBlaster: Continual Cross-Task CUDA Optimization via Memory-Augmented In-Context Reinforcement Learning
by: Dong, Kris Shengjun, et al.
Published: (2026)

From Plausible to Causal: Counterfactual Semantics for Policy Evaluation in Simulated Online Communities
by: Goyal, Agam, et al.
Published: (2026)

When Continual Learning Moves to Memory: A Study of Experience Reuse in LLM Agents
by: Hu, Qisheng, et al.
Published: (2026)

FASQ: Flexible Accelerated Subspace Quantization for Calibration-Free LLM Compression
by: Qiao, Ye, et al.
Published: (2026)

LLM Benchmark Datasets Should Be Contamination-Resistant
by: Al-Lawati, Ali, et al.
Published: (2026)

RADAR: Mechanistic Pathways for Detecting Data Contamination in LLM Evaluation
by: Kattamuri, Ashish, et al.
Published: (2025)

Trace-Level Analysis of Information Contamination in Multi-Agent Systems
by: Mazhar, Anna, et al.
Published: (2026)

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

Hierarchical Reinforcement Learning with Augmented Step-Level Transitions for LLM Agents
by: Zhen, Shuai, et al.
Published: (2026)

Breaking Bad Tokens: Detoxification of LLMs Using Sparse Autoencoders
by: Goyal, Agam, et al.
Published: (2025)

NextMem: Towards Latent Factual Memory for LLM-based Agents
by: Zhang, Zeyu, et al.
Published: (2026)

MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent
by: Yu, Hongli, et al.
Published: (2025)

All Leaks Count, Some Count More: Interpretable Temporal Contamination Detection and Mitigation in LLM Backtesting
by: Zhang, Zeyu, et al.
Published: (2026)

Exploring Multi-Modal Data with Tool-Augmented LLM Agents for Precise Causal Discovery
by: Shen, ChengAo, et al.
Published: (2024)

Agentopic: A Generative AI Agent Workflow for Explainable Topic Modeling
by: Kok-Shun, Brice Valentin, et al.
Published: (2026)

ABBEL: LLM Agents Acting through Belief Bottlenecks Expressed in Language
by: Lidayan, Aly, et al.
Published: (2025)

Search-Time Data Contamination
by: Han, Ziwen, et al.
Published: (2025)

EvolveMem:Self-Evolving Memory Architecture via AutoResearch for LLM Agents
by: Liu, Jiaqi, et al.
Published: (2026)

Procedural Memory Is Not All You Need: Bridging Cognitive Gaps in LLM-Based Agents
by: Wheeler, Schaun, et al.
Published: (2025)

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

MARK: Memory Augmented Refinement of Knowledge
by: Ganguli, Anish, et al.
Published: (2025)

Intelligently Augmented Contrastive Tensor Factorization: Empowering Multi-dimensional Time Series Classification in Low-Data Environments
by: Arunan, Anushiya, et al.
Published: (2025)

SAMEP: A Secure Protocol for Persistent Context Sharing Across AI Agents
by: Masoor, Hari
Published: (2025)

FiSH: Fair Spatial Hotspots
by: P, Deepak, et al.
Published: (2021)

Preference Leakage: A Contamination Problem in LLM-as-a-judge
by: Li, Dawei, et al.
Published: (2025)

StateLinFormer: Stateful Training Enhancing Long-term Memory in Navigation
by: Chen, Zhiyuan, et al.
Published: (2026)

ActionEngine: From Reactive to Programmatic GUI Agents via State Machine Memory
by: Zhong, Hongbin, et al.
Published: (2026)

Addressing LLM Diversity by Infusing Random Concepts
by: Agrawal, Pulin, et al.
Published: (2026)

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

Is One Score Enough? Rethinking the Evaluation of Sequentially Evolving LLM Memory
by: Dong, Songwei, et al.
Published: (2026)

AriadneMem: Threading the Maze of Lifelong Memory for LLM Agents
by: Zhu, Wenhui, et al.
Published: (2026)