agent/papers/items/2026-2607-14651-mempoison-uncovering-persistent-memory-threats-and-structural-blind-spots-in-llm.md

Paper: MemPoison: Uncovering Persistent Memory Threats and Structural Blind Spots in LLM Agents

---

type: paper title: "MemPoison: Uncovering Persistent Memory Threats and Structural Blind Spots in LLM Agents" authors: Jifeng Gao, Kang Xia, Yi Zhang, Xiaobin Hong, Mingkai Lin, Xingshen Wei, Wenzhong Li, Sanglu Lu year: 2026 venue: arXiv url: https://arxiv.org/abs/2607.14651 code_url: source: arxiv collected_at: 2026-07-27 published_at: 2026-07-16 updated_at: 2026-07-16 status: queued relevance: high topics:

• agent-evaluation
• agent-safety
• memory
• rag
• tool-use methods:

benchmarks:

models:

datasets:

• cs.CR related_concepts:

related_jobs:

related_experiments:

related_projects:

collection_score: 20 collection_queries: llm-agent

One-line Takeaway

Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.

Why Collected

• matched queries: llm-agent
• inferred topics: agent-evaluation, agent-safety, memory, rag, tool-use
• arXiv categories: cs.CR
• collection score: 20

Review Checklist

• Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
• Does it include a benchmark, dataset, code, or reproducible experimental setup?
• Should it be promoted from queued to skimmed or summarized?

Links

• arXiv: https://arxiv.org/abs/2607.14651