arXiv AI October 23, 2026 By Tanqiu Jiang, Min Bai, Sadat Shahriar, Wanyu Du, Sandesh Swamy

PerMIT: Securing Persistent Memory for LLM Agents via Machine-Checked Integrity Theorems and Scalable Community Trust

PerMIT is a memory architecture that provides provable integrity guarantees for persistent memory used by large language model agents. It limits trust to user‑typed inputs and values confirmed at a gate, mediating untrusted environment‑derived values through a finite interface while preserving multi‑turn planning and tool choice. Two machine‑checked integrity theorems in Lean 4 ensure that only gate‑confirmed data can influence sensitive actions, and community endorsements can accumulate to reduce verification effort as the user base grows.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Machine Learning

Jun 25

Forget to Improve: On-Device LLM-Agent Continual Learning via Budget-Curated Memory

arXiv:2606. 25115v1 Announce Type: new Abstract: On-device language-model agents improve by accumulating experience in retrieved memory rather than by updating weights.

By Beining Wu, Zihao Ding, Jun Huang, Yanxiao Zhao

llms agents robotics benchmarks

arXiv AI

Sep 30

Trojan Hippo Bench: A Dynamic Benchmark for Persistent Memory Attacks and Defenses in LLM Agents

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...

By Debeshee Das, Julien Piet, Darya Kaviani, Luca Beurer-Kellner, Florian Tram\`er, David Wagner

llms rag agents multimodal benchmarks safety

arXiv AI

Sep 1

SIR: Self-improving Red-teaming for Compute Use Agents

arXiv:2608.30207v1 Announce Type: cross Abstract: Computer use agents (CUAs) are vision-language models that perceive a screen and act on a real operating system through mouse, keyboard, and terminal...

By Chen Xiong, Zhiyuan He, Pin-Yu Chen, Stjepan Picek, Tsung-Yi Ho

llms agents multimodal benchmarks safety

arXiv AI

Jul 31

MemSecBench: Tracking Agent Memory Poisoning from Persistence to Consequence and Repair

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.

By Xuanze Chen, Xukang Xie, Wentao Fu, Jiajun Zhou, Shanqing Yu, Qi Xuan

llms agents benchmarks

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.

By Jinghan Xu, Yiyong Xiao, Wanru Shao, Hankai Liu, Xinjin Li

llms agents multimodal

arXiv AI

Jul 7

When Claws Remember but Do Not Tell: Stealthy Memory Injection in Persistent Personal Agents

arXiv:2607. 05189v1 Announce Type: cross Abstract: Persistent personal agents combine long-term memory with access to users' external environments, enabling personalized foreground assistance and proactive background execution.

By Yechao Zhang, Shiqian Zhao, Jiawen Zhang, Jie Zhang, Gelei Deng, Xiaogeng Liu, Chaowei Xiao, Tianwei Zhang

llms agents reinforcement-learning fine-tuning benchmarks

One email a morning, machine-written

Related stories

Forget to Improve: On-Device LLM-Agent Continual Learning via Budget-Curated Memory

Trojan Hippo Bench: A Dynamic Benchmark for Persistent Memory Attacks and Defenses in LLM Agents

SIR: Self-improving Red-teaming for Compute Use Agents

MemSecBench: Tracking Agent Memory Poisoning from Persistence to Consequence and Repair

Memory Provenance Laundering in LLM Agents: A Non-Amplification Firewall for Persistent Memory

When Claws Remember but Do Not Tell: Stealthy Memory Injection in Persistent Personal Agents