1 citations · 1 across the 3 of their papers we have counts for
3 papers · 1 filter
Learning to Report Unsafe Tasks in a Multi-Agent Game
Avyay M. Casheekar, Hariganesh Tangirala
When a team of agents shares a reward for completed tasks, reporting and stopping unsafe work reduces the team's reward. Random audits that penalize silence can make universal repo…
When Is an Agent Evaluation Over? Outcome Finality and Cross-Unit Separation
Avyay M. Casheekar, Hariganesh Tangirala
Agent evaluations commonly score the state observed when a run stops and count the run as one trial. Interpreting that score as a final result from a separate trial requires outcom…
Adapting Probabilistic Risk Assessment for AI
Anna Katariina Wisakanto, Joe Rogero, Avyay M. Casheekar +1
Modern general-purpose artificial intelligence (AI) systems present an urgent risk management challenge, as their rapidly evolving capabilities and potential for catastrophic harm…