Agent Against Agent: An Agentic System for Automatic Prompt Injection Red Teaming

• 类型：arxiv
• 标识：2608.05108
• 链接：https://arxiv.org/abs/2608.05108
• 主分类：agent
• 形态：method
• 被引：0
• 被引来源：Semantic Scholar
• S2被引：0
• 影响力被引：0
• TLDR：PIMiner is developed, an agentic system for prompt injection red-teaming that builds a strategy library from scratch during training and can be directly transferred to a previously unseen target LLM without additional training at test time.
• 副分类：risk
• 待LLM分类：否
• 标题中文：Agent Against Agent：面向自动提示注入红队测试的智能体系统
• TLDR中文：开发 PIMiner，一种用于 prompt injection 红队的 agentic 系统，可在训练阶段从零构建策略库，并在测试时无需额外训练直接迁移到未见过的目标 LLM。
• 来源文件：
• /inbox/tom/_candidates/2026-08-06-agent-rag-longcontext-candidates.json
• [S2 enrich]