To study this phenomenon, SocioHack is introduced, a sandbox of 72 societal environments, and it is found that within these environments, reward hacking naturally emerges and leads to regulatory loophole discovery.
Wei Liu, Xinyi Mou, Hanqi Yan et al.· arXiv.org· 3 citations
The Detection-Aware Attribution Framework is proposed, which learns the effects of valid attribute replacements and amortizes this intervention evidence into deployment-time diagnosis, and shows that intervention-grounded attribute attribution can connect failure localization to executable system repair.
State-Grounded Conditioning is introduced, a design principle for user-facing LLM agents that must condition on live user state (game state, session history, live inventory), and a distinct failure class the authors call direction drift: task-complete responses whose chosen direction misaligns with the current state.
Qi Liu, Xiao-Yang Yuan, Yu-Bin Ruan et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.