When Correct Memory Goes Wrong: Fuzzing Persistent Memory Use in LLM Agents
cs.DC, cs.AI
Submitted: 2026-09-29
Updated: 2026-09-29
Sources
- Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
- Memory Injection Attacks on LLM Agents via Query-Only Interaction
- When Knowledge Changes: Metamorphic Testing of RAG Systems with Mutations
- Testing Retrieval-Augmented Generation Systems with Chunk Coverage
- EquiMem: Calibrating Shared Memory in Multi-Agent Debate via Game-Theoretic Equilibrium
- Context manipulation attacks : Web agents are susceptible to corrupted memory
- Zep: A Temporal Knowledge Graph Architecture for Agent Memory
- The Trap of Trajectory: Towards Understanding and Mitigating Spurious Correlations in Agentic Memory
- A-MemGuard: A Proactive Defense Framework for LLM-Based Agent Memory
Related papers
- iScheduler: Reinforcement Learning-Driven Continual Optimization for Large-Scale Resource Investment Problems
- SAMM: Sharded Automated Market Maker
- InferScale: GPU-Native KV Injection for Personalized LLM Serving
- Vigil: Accountable Liveness against Selective Silence
- Steelhead: Interleaving Partially Synchronous and Asynchronous Commit Rules on a Shared DAG
- Democratizing MoE inference on commodity GPUs with CoMoE