MAPLE-Guard: Memory-Aware Link Enforcement Against Memory-Link Poisoning in Multi-Agent Systems
cs.MA, cs.CR
Submitted: 2026-08-01
Updated: 2026-10-03
Comments: 27 pages, 14 figures, 9 tables. Includes examples that may be misleading or harmful. Code: https://github.com/xiong-wenjun/MAPLE-Guard
Code: https://github.com/xiong-wenjun/MAPLE-Guard
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents
- Geometrically-Constrained Agent for Spatial Reasoning
- Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
- From Untrusted Input to Trusted Memory: A Systematic Study of Memory Poisoning Attacks in LLM Agents
- Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations
- A Survey on Long-Term Memory Security in LLM Agents: Attacks, Defenses, and Governance Across the Memory Lifecycle
- AgentSafe: Safeguarding Large Language Model-based Multi-agent Systems via Hierarchical Data Management
- Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens
- MemGPT: Towards LLMs as Operating Systems
- SMSR: Certified Defence Against Runtime Memory Poisoning in Persistent LLM Agent Systems
- MemoryGraft: Persistent Compromise of LLM Agents via Poisoned Experience Retrieval
- Memory poisoning and secure multi-agent systems
- AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation
- Who's the Mole? Modeling and Detecting Intention-Hiding Malicious Agents in LLM-Based Multi-Agent Systems
- MemRL: Self-Evolving Agents via Runtime Reinforcement Learning on Episodic Memory
- Memento: Fine-tuning LLM Agents without Fine-tuning LLMs
- INFA-Guard: Mitigating Malicious Propagation via Infection-Aware Safeguarding in LLM-Based Multi-Agent Systems
- Exploring Agentic Tool-Calling Decisions via Uncertainty-Aligned Reinforcement Learning
Related papers
- Highway Congestion Reduction through Reinforcement Learning Based Eulerian Headway Control
- You Only Align Once: Propagating Cooperative Behaviors in Multi-Agent Systems through Seed Agents
- Deny Without Disabling: Authorization-Paired Evaluation and Control for Multi-Agent Systems
- MA-SAPO: Multi-Agent Reasoning for Score-Aware Prompt Optimization
- PeroMAS: A Multi-agent System of Perovskite Material Discovery
- StitchCUDA: An Automated Multi-Agents End-to-End GPU Programing Framework with Rubric-based Agentic Reinforcement Learning