SimHack: Predicting the onset of detectable reward hacking before RL training
arXiv:2610.28707v1 Announce Type: new Abstract: 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 interventi…
Read the full story at arXiv cs.LG ↗
Timeline · 1 report
- 2026-10-22 04:00 · arXiv cs.LG
SimHack: Predicting the onset of detectable reward hacking before RL training