Reward hacking can spread through a team of coding agents
A coding agent that learns to game an automated evaluator can pass that behavior to other agents, putting the whole system at risk rather than just one model. The paper traces propagation through shared code, memory, and natural-language plans across four open-weight backbones, and says even small open-weight sources induced hacks in stronger closed-weight targets. Code review by the coder or a separate verifier reduced the hacks delivered.