arXiv AI
Semantic-TVM: Structure-Preserving Trustworthy Virtual Memory for Memory-Augmented and Tool-Using Agents
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Aug 3
Memory Provenance Laundering in LLM Agents: A Non-Amplification Firewall for Persistent Memory
arXiv:2607. 29167v1 Announce Type: cross Abstract: Long-term memory lets large language model(LLM) agents reuse prior preferences and work flows, but it also turns untrusted observations into persistent action context.
arXiv Machine Learning
Jun 18
GateMem: Benchmarking Memory Governance in Multi-Principal Shared-Memory Agents
arXiv:2606. 18829v1 Announce Type: new Abstract: Memory benchmarks for LLM agents largely assume single-user settings, leaving shared assistants for hospitals, workplaces, campuses, and households understudied.
arXiv AI
Oct 21
ClawMMU: Protection-Coherent Virtual Memory for Stateful LLM Agents
ClawMMU is a protection layer for large language model agents that tags every memory fragment with its owner, scope, origins, and authority. It enforces that information can only increase in authority but never self‑elevate, checking these labels whenever content enters the model’s context, is stored, retrieved, or used to drive tool calls. By basing checks on provenance rather than content, ClawMMU turns memory attacks into classical protection faults that the agent harness can block even if the model is misled.
arXiv AI
Jul 7
PLACEMEM: Toward a Compute-Aware Memory Plane for Lifelong Agents
arXiv:2607. 04089v1 Announce Type: new Abstract: Lifelong agents need more than larger context windows and better retrieval.
arXiv AI
Sep 21
CIPL: A Channel-Aware Framework for Recoverable Privacy Leakage in LLM Agents
CIPL (Channel Inversion for Privacy Leakage) is a channel-aware framework designed to evaluate black-box privacy leakage in large language model agents. It models the leakage process through stages of sensitive source, selection, assembly, execution, observation, and extraction, assessing how selected sensitive units become attacker-recoverable outputs. Experiments across memory, retrieval, and tool-mediated targets, plus a live-agent case study, reveal that recoverability depends on factors beyond storage labels, such as observation surface, prompt alignment, retrieval depth, and provider behavior, and that a semantic audit can uncover disclosures missed by exact matching.
arXiv AI
Jun 12
A Survey on Long-Term Memory Security in LLM Agents: Attacks, Defenses, and Governance Across the Memory Lifecycle
arXiv:2604. 16548v2 Announce Type: replace-cross Abstract: The emergence of writable, cross-session persistent memory in LLM agents introduces a qualitatively different threat landscape from conventional input-centric security concerns, characterized by three properties: persistence, statefulness, and propagation.