Cover Image

Hidden in Memory: Sleeper Memory Poisoning in LLM Agents

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Pulipaka, Sidharth, Hlebik, Stanislau, Raghav, Leonidas, Abdelnabi, Sahar, Raina, Vyas, Sheth, Ivaxi, Fritz, Mario
Format:	Preprint
Published:	2026
Subjects:	Cryptography and Security Artificial Intelligence D.4.6; I.2.7; I.2.11
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

PersistBench: When Should Long-Term Memories Be Forgotten by LLMs?
by: Pulipaka, Sidharth, et al.
Published: (2026)

MEMTIER: Tiered Memory Architecture and Retrieval Bottleneck Analysis for Long-Running Autonomous AI Agents
by: Sidik, Bronislav, et al.
Published: (2026)

ScrapMem: A Bio-inspired Framework for On-device Personalized Agent Memory via Optical Forgetting
by: Chang, Jiale, et al.
Published: (2026)

Terrarium: Revisiting the Blackboard for Multi-Agent Safety, Privacy, and Security Studies
by: Nakamura, Mason, et al.
Published: (2025)

Post Hoc Extraction of Pareto Fronts for Continuous Control
by: Thakar, Raghav, et al.
Published: (2026)

Applying Cognitive Design Patterns to General LLM Agents
by: Wray, Robert E., et al.
Published: (2025)

Agent Capsules: Quality-Gated Granularity Control for Multi-Agent LLM Pipelines
by: Ray, Aninda
Published: (2026)

PARNESS: A Paper Harness for End-to-End Automated Scientific Research with Dynamic Workflows, Full-Text Indexing, and Cross-Run Knowledge Accumulation
by: Wang, Yuchen, et al.
Published: (2026)

Do We Always Need Query-Level Workflows? Rethinking Agentic Workflow Generation for Multi-Agent Systems
by: Wang, Zixu, et al.
Published: (2026)

PRIMA: Operational Patterns for Resilient Multi-Agent Research with Verifiable Identity and Convergent Feedback
by: Annapureddy, Sasank
Published: (2026)

Exploring Design of Multi-Agent LLM Dialogues for Research Ideation
by: Ueda, Keisuke, et al.
Published: (2025)

Instruction-Level Weight Shaping: A Framework for Self-Improving AI Agents
by: Costa, Rimom
Published: (2025)

MemForest: An Efficient Agent Memory System with Hierarchical Temporal Indexing
by: Chen, Han, et al.
Published: (2026)

Multi-Paradigm Agent Interaction in Practice:A Systematic Analysis of Generator-Evaluator, ReAct Loop,and Adversarial Evaluation in the buddyMe Framework
by: Wang, Xiaohua, et al.
Published: (2026)

Governance Architecture for Autonomous Agent Systems: Threats, Framework, and Engineering Practice
by: Ge, Yuxu
Published: (2026)

Council Mode: A Heterogeneous Multi-Agent Consensus Framework for Reducing LLM Hallucination and Bias
by: Wu, Shuai, et al.
Published: (2026)

Harnessing Embodied Agents: Runtime Governance for Policy-Constrained Execution
by: Qin, Xue, et al.
Published: (2026)

Good to Go: The LOOP Skill Engine That Hits 99% Success and Slashes Token Usage by 99% via One-Shot Recording and Deterministic Replay
by: Wang, Xiaohua, et al.
Published: (2026)

Beyond Rating: A Comprehensive Evaluation and Benchmark for AI Reviews
by: Li, Bowen, et al.
Published: (2026)

TRIZ Agents: A Multi-Agent LLM Approach for TRIZ-Based Innovation
by: Szczepanik, Kamil, et al.
Published: (2025)

CRAwDAD: Causal Reasoning Augmentation with Dual-Agent Debate
by: Vamosi, Finn G., et al.
Published: (2025)

Agent WARPP: Workflow Adherence via Runtime Parallel Personalization
by: Mazzolenis, Maria Emilia, et al.
Published: (2025)

Latent Cache Flow: Model-to-Model Communication Without Text
by: Rossi, Maximillian, et al.
Published: (2026)

Umwelt Engineering: Designing the Cognitive Worlds of Linguistic Agents
by: Jehu-Appiah, Rodney
Published: (2026)

GSAR: Typed Grounding for Hallucination Detection and Recovery in Multi-Agent LLMs
by: Kamelhar, Federico A.
Published: (2026)

Collaborative LLM Agents for C4 Software Architecture Design Automation
by: Szczepanik, Kamil, et al.
Published: (2025)

Fuzzy, Symbolic, and Contextual: Enhancing LLM Instruction via Cognitive Scaffolding
by: Figueiredo, Vanessa
Published: (2025)

Generative AI Toolkit -- a framework for increasing the quality of LLM-based applications over their whole life cycle
by: Kohl, Jens, et al.
Published: (2024)

FSFM: A Biologically-Inspired Framework for Selective Forgetting of Agent Memory
by: Gu, Yingjie, et al.
Published: (2026)

Tool-RoCo: An Agent-as-Tool Self-organization Large Language Model Benchmark in Multi-robot Cooperation
by: Zhang, Ke, et al.
Published: (2025)

AgentAtlas: Beyond Outcome Leaderboards for LLM Agents
by: Mazaheri, Parsa, et al.
Published: (2026)

elsciRL: Integrating Language Solutions into Reinforcement Learning Problem Settings
by: Osborne, Philip, et al.
Published: (2025)

ART: Adaptive Response Tuning Framework -- A Multi-Agent Tournament-Based Approach to LLM Response Optimization
by: Khan, Omer Jauhar
Published: (2025)

AgentLeak: A Full-Stack Benchmark for Privacy Leakage in Multi-Agent LLM Systems
by: Yagoubi, Faouzi El, et al.
Published: (2026)

Advancing Multimodal Agent Reasoning with Long-Term Neuro-Symbolic Memory
by: Jiang, Rongjie, et al.
Published: (2026)

From Helpfulness to Toxic Proactivity: Diagnosing Behavioral Misalignment in LLM Agents
by: Wang, Xinyue, et al.
Published: (2026)

MEMSAD: Gradient-Coupled Anomaly Detection for Memory Poisoning in Retrieval-Augmented Agents
by: Gowda, Ishrith
Published: (2026)

Contrastive Learning-Enhanced Large Language Models for Monolith-to-Microservice Decomposition
by: Sellami, Khaled, et al.
Published: (2025)

Understanding Multi-Agent LLM Frameworks: A Unified Benchmark and Experimental Analysis
by: Orogat, Abdelghny, et al.
Published: (2026)

Compiled AI: Deterministic Code Generation for LLM-Based Workflow Automation
by: Trooskens, Geert, et al.
Published: (2026)