While recent advances in autonomous agents enable them to coordinate on increasingly complex tasks, prior work shows that this growing capacity for coordination can create safety risks, including collusion, in which agents jointly pursue misaligned actions while concealing the true basis of those actions from oversight...
Eric Onyame, Run Zhou, Kowshik Thopalli et al.· 0 citations
While AI weather models now rival operational forecasts, how they represent the atmosphere internally remains an open question: feature attribution reveals which input patterns matter, not what the model computes or how it combines information internally. We train sparse autoencoders (SAEs) on GraphCast to uncover its...
Madelyn Mathai, Timothy B. Higgins, K. Grise et al.· 1 citation
MEA is presented, a multi-agent framework that removes the explanation knowledge barrier entirely, and suggests that AI agents themselves can serve as a scalable, adaptable interface to ML explainability, opening a path toward natural-language explainability that generalizes beyond the fixed, single-purpose tools that...
