Reproduce “SEAL: Towards Persistent Tool Poisoning Attack against LLM Agents via Prefix-Eliciting Trigger” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Nanjun Zhou, Yiming Li, Yukun Chen, Ting Qiao, Enhao Huang, Zhan Qin
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.