mlsanityData to 14 Oct 2026

Semantic-TVM: Structure-Preserving Trustworthy Virtual Memory for Memory-Augmented and Tool-Using Agents

arXiv 2609.15011 ↗First posted 14 Sep 2026cs.AIcited by 0

On the map: LLM agents and tool use → Agent memory systems

Abstract (arXiv)

Memory-augmented and tool-using agents expose exact private values when remote LLMs process retrieved memory, tool actions, and intermediate observations. One-way masking limits direct exposure but removes values needed for trusted execution and can leak them through later observations. We propose Trustworthy Virtual Memory (TVM), a closed-loop runtime that keeps exact-value state local while presenting a protected view to the remote model. Within this single runtime, Rule-TVM replaces whole protected fields with locally recoverable handles, and Semantic-TVM instead replaces only sensitive spans predicted by a trusted local model, preserving surrounding task-relevant context. On Memory-EHR and Memory-RAP across two providers, span-level projection recovers most of the EHR utility lost under whole-field replacement (Task Success 84.17% vs. 52.33% on DeepSeek) while measured exposure stays low and workflows remain executable.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Agent memory systems, one of 16 directions in LLM agents and tool use. Builds on 11 of its 14 references that are in the map. First posted on arXiv 14 Sep 2026.

Builds on

11 of 14 references.

References · 11

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  3. 2023Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injectioncited by 1,443
  4. 2024AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Basescited by 429
  5. 2023Formalizing and Benchmarking Prompt Injection Attacks and Defensescited by 364
  6. 2025Unveiling Privacy Risks in LLM Agent Memorycited by 101
  7. 2024EHRAgent: Code Empowers Large Language Models for Few-shot Complex Tabular Reasoning on Electronic Health Recordscited by 78
  8. 2024PAPILLON: Privacy Preservation from Internet-based and Local Language Model Ensemblescited by 57
  9. 2026PlanTwin: Privacy-Preserving Planning Abstractions for Cloud-Assisted LLM Agentscited by 3
  10. 2026Minim: Privacy-Aware Minimal View for Agents via Trusted Local Sanitizationcited by 2
  11. 2026SlotGuard: Stop Oversharing Private Local Context in LLM Agent Transcricited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Memory Provenance Laundering in LLM Agents: A Non-Amplification Firewall for Persistent Memory
  2. 2026ClawVM: Harness-Managed Virtual Memory for Stateful Tool-Using LLM Agents
  3. 2026MAP-Graph: Provenance-Aware Shared Memory for Multi-Agent Workflows
  4. 2026A Survey on Long-Term Memory Security in LLM Agents: Attacks, Defenses, and Governance Across the Memory Lifecycle
  5. 2026Governed Persistent Memory: Source-Bound State Semantics and Fail-Closed Release for Long-Horizon Agents
  6. 2026Beyond Similarity: Trustworthy Memory Search for Personal AI Agents
  7. 2026MemLineage: Lineage-Guided Enforcement for LLM Agent Memory
  8. 2025Collaborative Memory: Multi-User Memory Sharing in LLM Agents with Dynamic Access Control