Emergent Strategic Reasoning Risks in AI: A Taxonomy-Driven Evaluation Framework
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). These include, but are not limited to, deception (intentionally misleading users or evaluators), evaluation gaming (strategically manipulating performance during safety testing), and reward hacking (exploiting misspecifie
By Tharindu Kumarage, Lisa Bauer, Yao Ma, Dan Rosen, Yashasvi Raghavendra Guduri, Anna Rumshisky, Kai-W