Reproduce “Reachability-Based Capability Confinement for LLM Agents under Indirect Prompt Injection” 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
Wujie Xiong, Rabimba Karanjai, Yang Lu, Weidong Shi, Lei Xu
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.