GT-HarmBench is a benchmark that evaluates AI safety risks in multi-agent settings, covering 1,535 high-stakes scenarios based on game-theoretic structures like the Prisoner's Dilemma, Stag Hunt, and Chicken. The benchmark draws scenarios from realistic AI risk contexts in the MIT AI Risk Repository and tests 15 frontier models, finding that agents fail to choose socially beneficial actions in 38% of cases, including military escalation, election manipulation, and medical malpractice. The study also measures how prompt framing and ordering affect outcomes and shows that game-theoretic interventions can improve socially beneficial outcomes by up to 18%.
arXiv:2604. 22119v2 Announce Type: replace Abstract: As reasoning capacity and deployment scope grow in tandem, large language models (LLMs) gain the capacity to engage in behaviors that serve their own objectives, a class of risks we term Emergent Strategic Reasoning Risks (ESRRs).
arXiv:2604. 02022v4 Announce Type: replace Abstract: Evaluating the safety of LLM-based agents is increasingly important because risks in realistic deployments often emerge over multi-step interactions rather than isolated prompts or final responses.
arXiv:2602. 16666v3 Announce Type: replace Abstract: AI agents are increasingly deployed to execute important tasks.
arXiv:2608. 01193v1 Announce Type: cross Abstract: An AI development race creates a multi-agent safety dilemma.
arXiv:2607. 25485v1 Announce Type: new Abstract: Health AI is evolving from answering questions to agentic systems that converse with patients, reason about health records, and act on their behalf.
arXiv:2606. 15385v1 Announce Type: new Abstract: Reward hacking, where AI systems exploit misspecified objectives to achieve high reward without satisfying intended goals, remains a central challenge in AI safety.
LLM-based agents leverage third-party skills to extend their capabilities in open-world scenarios. However, third-party skills can introduce extra security vulnerabilities, as seemingly harmless skills can contain latent safety risks that only emerge during actual execution.
arXiv:2605. 28591v2 Announce Type: replace-cross Abstract: The validity of AI safety evaluations depends on models behaving consistently across controlled and deployment settings.
arXiv:2607. 18366v1 Announce Type: new Abstract: Large language models (LLMs) serving as planners in tool-using autonomous agents introduce dynamic reliability risks in multi-turn execution.
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.
arXiv:2608. 03166v1 Announce Type: new Abstract: Role-Playing Language Agents (RPLAs) are increasingly deployed in high-stakes applications such as healthcare assistance, customer support, and education, where maintaining consistent personas, ethical constraints, and behavioral coherence under adversarial pressure is critical.
arXiv:2510. 09330v3 Announce Type: replace Abstract: Ensuring that large language models (LLMs) comply with safety requirements is a central challenge in AI deployment.