RL2 min read
SimHack: Predicting the onset of detectable reward hacking before RL training
When training LLMs to code with reinforcement learning, reward hacking is often detectable but difficult to prevent, since (a) environment hardening is increasingly difficult as training environments grow more complex; and (b) training-time interventions incentivize models to obfuscate hacking…
By Junwei Deng, Alex Bie, Natalia PonomarevaarXiv cs.LG
Read the full story
Originally published by arXiv cs.LG on Oct 22, 2026.
Comments
Sign in to join the discussion.