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: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.
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:2607. 04089v1 Announce Type: new Abstract: Lifelong agents need more than larger context windows and better retrieval.
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: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.
arXiv:2610.31840v1 Announce Type: new Abstract: Tool-calling agents are mostly optimized for accuracy; in deployment, however, their growing cost is latency: every tool call is decoded autoregressive...
arXiv:2602.22402v2 Announce Type: replace-cross Abstract: As large language models engage in extended reasoning tasks, they accumulate significant state -- architectural mappings, trade-off decisions...
arXiv:2605.01970v4 Announce Type: replace-cross Abstract: Memory systems enable otherwise stateless LLM agents to persist user information across sessions, but also introduce a new attack surface. Th...
arXiv:2606. 06054v1 Announce Type: new Abstract: Personal AI agents increasingly rely on long-term memory to provide persistent personalization across sessions.
The paper proposes the Analytical Memory Unit (AMU), a memory schema that attaches a full derivation (lineage) graph to every cached result in enterprise AI agents. By gating retrieval with a policy that requires authorization for every column touched, the authors prove that sensitive columns cannot be leaked through derived results, achieving up to 90% lineage completeness to eliminate leakage. Experiments show lineage‑gated retrieval removes 18.8‑25.5% of cross‑department leakage while maintaining 81.5‑82.6% memory reuse with minimal overhead, and a real‑agent proof‑of‑concept demonstrates zero leaks over multiple interactions.
arXiv:2607. 09493v1 Announce Type: new Abstract: Agentic LLM systems that generate code through multi-turn tool use face a fundamental context problem: each session starts from zero, discarding the configuration choices, domain constraints, data schemas, and tool-use patterns that made previous sessions productive.