paperSeptember 2026Unreviewed

SchemeArena: Factorized Stress Testing of Scheming in LLM Agents

Jie Ruan, Inderjeet Nair, Amy Liu, Muhammad Khalifa, Yusheng Zhou, Lu Wang

Abstract

We study scheming in LLM agents, in which agents covertly pursue misaligned goals. Our focus is to understand how scheming arises from the interaction of key factors, such as instrumental goals, environmental affordances, oversight conditions, and perceived consequences. Prior work examines only a small number of scenarios, limiting the ability to isolate how these conditions shape an agent's propensity or capability to scheme. This limited scale and task diversity also restrict coverage of real

Cite

@misc{ruan2026schemearena,
  title = {{SchemeArena: Factorized Stress Testing of Scheming in LLM Agents}},
  author = {Jie Ruan and Inderjeet Nair and Amy Liu and Muhammad Khalifa and Yusheng Zhou and Lu Wang},
  year = {2026},
  month = sep,
  eprint = {2609.08126},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.08126}
}