agent/papers/items/2026-2605-18930-oep-poisoning-self-evolving-llm-agents-via-locally-correct-but-non-transferable-.md

Paper: OEP: Poisoning Self-Evolving LLM Agents via Locally Correct but Non-Transferable Experiences

---

type: paper title: "OEP: Poisoning Self-Evolving LLM Agents via Locally Correct but Non-Transferable Experiences" authors: Kaixiang Wang, Jiong Lou, Zhaojiacheng Zhou, Jie Li year: 2026 venue: arXiv url: https://arxiv.org/abs/2605.18930 code_url: source: arxiv collected_at: 2026-07-08 published_at: 2026-05-18 updated_at: 2026-05-18 status: queued relevance: high topics:

• agent-evaluation
• agent-safety
• memory
• reasoning methods:

benchmarks:

models:

datasets:

• cs.CR
• cs.AI
• cs.LG related_concepts:

related_jobs:

related_experiments:

related_projects:

collection_score: 17 collection_queries: agent-memory

One-line Takeaway

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

Why Collected

• matched queries: agent-memory
• inferred topics: agent-evaluation, agent-safety, memory, reasoning
• arXiv categories: cs.CR, cs.AI, cs.LG
• collection score: 17

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/2605.18930