Monitoring and Discovering Reward Hacking with Internal Representations during LLM Evaluations
This work measures the high prevalence of reward hacking in SWE-style evaluations of frontier open-weight LLMs (Kimi K3, GLM 5.2, Qwen 3.8 Max) and shows that simple difference-of-means (DoM) vectors built from synthetic data coherently represent reward hacking, detect it at near-LLM-monitor effectiveness and virtually no cost, predict hacks in subsequent actions, and transfer to non-SWE environments to surface cheating behaviors not covered by predefined rubrics.