arXiv:2607. 14651v1 Announce Type: cross Abstract: Persistent external memory enhances agent continuity but introduces persistent security vulnerabilities: adversarial content can be injected via standard interaction channels, retained across turns, and later distort downstream behavior.
arXiv:2607. 27080v1 Announce Type: cross Abstract: Memory systems allow agents to retain and reuse information from past interactions, but they can also let malicious content persist.
arXiv:2606. 04329v1 Announce Type: cross Abstract: Memory is a core component of AI agents, enabling them to accumulate knowledge across interactions and improve performance.
arXiv:2608. 07622v1 Announce Type: new Abstract: Long-term memory enables AI agents to maintain continuity across sessions, personalize behavior, and evolve through accumulated experience.
arXiv:2605. 08442v5 Announce Type: replace-cross Abstract: We discover that prompt-injection success and tool-execution success are separable safety properties: defenses that block injection do not necessarily block execution, and vice versa.
As LLM agents increasingly rely on persistent memory for long-horizon and personalized behavior, they can retain and reuse information across interactions, but this also creates a lasting channel thro...
arXiv:2607. 10608v1 Announce Type: new Abstract: Memory is becoming a core component of long-horizon AI agents, allowing agents to reuse past experience when operating web browsers, software tools, and other interactive environments.
The paper introduces DREAM, a training‑free, agent‑intrinsic memory repair framework that selectively forgets poisoned memories in large language model agents. DREAM uses perturbation‑induced reactivation, anomaly detection on activation patterns, and dynamic suppression of harmful memories while reinforcing benign ones. Experiments show DREAM cuts backdoor attack success by over 95% and improves runtime and token efficiency compared to existing defenses.
Large language model agents are vulnerable to memory‑poisoning attacks, and existing defenses rely on external modules that are memory‑inefficient and computationally heavy. The paper introduces DREAM, a training‑free, agent‑intrinsic memory repair framework that uses weak reactivation to destabilize malicious memories, anomaly detection on activation patterns, and selective suppression of harmful memories while reinforcing benign ones. Experiments show DREAM cuts backdoor attack success by over 95 % and improves runtime and token efficiency compared to A‑MemGuard, while maintaining high task success on poisoned multi‑agent systems.
arXiv:2605. 08442v3 Announce Type: replace-cross Abstract: Persistent memory attacks against LLM agents achieve high attack success rates against open-source models.
arXiv:2606. 23195v2 Announce Type: replace Abstract: Large Language Model (LLM) agents increasingly rely on memory systems to maintain long-term coherence.
arXiv:2605.12978v2 Announce Type: replace Abstract: Learning from past experience benefits from two complementary forms of memory: episodic traces -- raw trajectories of what happened -- and consolid...