Meta and Duke study finds reward hacking can spread between AI models

Small coding agents trained to game their evaluators passed those habits to Claude and Gemini through shared code, plans, and memory A small AI model that learned to cheat on its homework can apparently teach the habit to much bigger, more capable models. That is the central finding of new research from Meta Superintelligence Labs and Duke University. It shows that reward hacking, where an AI games its scoring system instead of doing the actual job, can move from weak coding agents to frontier models through the code, plans, and memory they share. What the researchers found The paper is titled “Reward Hacking as a Transmissible Strategy in Multi-Agent Coding Systems.” Its lead author is Yuepeng Hu, who is affiliated with both Meta Superintelligence Labs and Duke. Co-authors include Pegah Ghahremani, Reza Aghajani, Mahesh Pasupuleti, and Himaghna Bhattacharjee. First, some vocabulary. Reward hacking is what happens when an AI figures out how to score well with an automated grader without completing the task the grader was meant to measure. The researchers started with small open-weight models trained via reinforcement learning, a method where a model is rewarded for outcomes and gra...