Advancing red teaming with people and AI

GPT-Red: Unlocking Self-Improvement for Robustness

Explore GPT-Red, OpenAI’s automated red teaming system that uses self-play to improve AI safety, alignment, and prompt injection robustness.

Introducing the Red-Teaming Resistance Leaderboard

GPT-Red: Automated Red Teaming via Self-Play at Scale

arXiv:2607. 26115v1 Announce Type: cross Abstract: We introduce \textbf{GPT-Red}, an automated red-teaming agent that is trained to discover novel prompt injection attacks against frontier LLMs.

Red-Teaming Large Language Models

NestRL: A Nested Training Regime for Mutual Adaptation in Human-AI Teaming

arXiv:2602. 17737v2 Announce Type: replace-cross Abstract: Mutual adaptation is a central challenge in human-AI teaming, as humans naturally adjust their strategies in response to an AI agent's behavior.

PersonaTeaming: Supporting Persona-Driven Red-Teaming for Generative AI

PersonaTeaming introduces a workflow that incorporates personas into adversarial prompt generation for generative AI, achieving higher attack success rates than the state‑of‑the‑art RainbowPlus while preserving prompt diversity. The system is extended into a user‑facing playground that lets red‑teamers create their own personas and collaborate with AI to refine prompts, fostering diverse strategies. A user study with 11 industry practitioners found the playground produced useful outputs and encouraged out‑of‑the‑box thinking, even when suggestions were not strictly followed.

What Types of Human-AI Teams Exist?

arXiv:2607. 02198v1 Announce Type: cross Abstract: Human-AI teaming has received increasing attention in the literature.

Human-AI Teaming Through the Lens of Calibration

arXiv:2606. 10906v1 Announce Type: cross Abstract: We study models for human-AI teaming through the lens of statistical calibration.

AI Evaluation Should Work With Humans

arXiv:2608. 13577v1 Announce Type: new Abstract: This position paper argues that the dominant paradigm of AI evaluation (which focuses on superhuman autonomous performance and so implicitly targets the goal of replacing humans) is guiding AI development in the wrong direction.

OpenAI Red Teaming Network

We’re announcing an open call for the OpenAI Red Teaming Network and invite domain experts interested in improving the safety of OpenAI’s models to join our efforts.

Searching for Synergy in Shared Workspace Human-AI Collaboration

arXiv:2606. 18413v1 Announce Type: new Abstract: Automated AI agents are increasingly capable, yet many scientific and professional tasks require human judgment and contextual expertise.

Institutional Red-Teaming: Deployment Rules, Not Just Models, Causally Shape Multi-Agent AI Safety

arXiv:2607. 07695v1 Announce Type: new Abstract: We introduce institutional red-teaming, an evaluation methodology for testing deployment rules in multi-agent AI: hold the agents, objectives, and task state fixed, vary only one rule, and attribute the resulting change in collective behavior to that rule.