Evolve the Method, Not the Prompts: Evolutionary Synthesis of Jailbreak Attacks on LLMs

ArXi:2511.12710v2 Announce Type: replace Automated red teaming frameworks for Large Language Models (LLMs) have become increasingly sophisticated, yet many still formulate attack optimization primarily in the prompt space. In other words, these methods mainly search for better attack wording or better strategy choices, but they do not search over executable code. By moving the search into code space, we can optimize not only the final attack prompt, but also the procedure that generates it, including execution flow, reusable logic, branching, and failure-driven repair.