AgentAntibody: An Adaptive Immune System for Defending LLM Agents against Prompt Injection

Abstract

Prompt injection remains a critical threat to LLM agents, yet existing defenses treat each task as a self-contained problem, independent of previous encounters. In practice, user requests are often underspecified: they describe the desired outcome without fully specifying acceptable behavior. An injection can exploit this ambiguity, causing the agent to complete the task in a way the user would reject. As the user's expectations become clearer through concrete cases, a defense should learn from

Categories

Framework mappings

Suggested from the entry's categories.

@misc{weng2026agentantibody,
  title = {{AgentAntibody: An Adaptive Immune System for Defending LLM Agents against Prompt Injection}},
  author = {Shihao Weng and Yang Feng and Xiaofei Xie and Jiongchi Yu},
  year = {2026},
  month = aug,
  eprint = {2608.04053},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2608.04053}
}