CART: Closed-Loop Adaptive Red Teaming for Large Language Models

CART (Closed‑Loop Adaptive Red Teaming) is a framework that iteratively uses results from red‑teaming tests to guide subsequent probes, thereby expanding risk coverage and maintaining diversity. It separates the roles of Challenger (test generator), Target (model or agent under test), and Judge (result evaluator), enabling independent study of each component. Across multiple evaluation families, CART uncovers more failures and higher risk than static prompt replay, demonstrating that adaptive, continuous testing reveals weaknesses that fixed‑prompt methods miss.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• llms
• agents