AutoRISE: Agent-Driven Strategy Evolution for Red-Teaming Large Language Models
Automated red-teaming methods for large language models typically optimize attack prompts within a fixed, human-designed strategy, leaving the attack strategy itself unchanged. We instead optimize the strategy. We propose AutoRISE, a method that searches over executable attack programs rather than individual prompts. At each iteration, a coding agent edits a strategy and a fixed evaluation harness scores the resulting attacks, returning both a scalar objective and per-example diagnostics that guide subsequent edits. This allows structural changes, including new attack components and altered control flow, that prompt-level methods do not directly express. We also release two benchmark suit...
| Authors | Tanmay Gautam, Alireza Bahramali, Sandeep Atluri |
|---|---|
| Primary category | cs.CR |
| Published | 23 April 2026 |
| Last updated at source | 23 April 2026 |
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.