Showing cs.AIShow all
3 papers · 1 filter
cs.AI2026
Calibrating Conservatism for Scalable Oversight
William Overman, Mohsen Bayati
Agentic AI systems capable of autonomous planning and extended environmental interaction pose a fundamental control problem: how can humans maintain meaningful oversight of systems…
cs.AI2026
The Oversight Game: Learning to Cooperatively Balance an AI Agent's Safety and Autonomy
William Overman, Mohsen Bayati
As increasingly capable agents are deployed, a central safety challenge is how to retain meaningful human control without modifying the underlying system. We study a minimal contro…
cs.AI2025
Conformal Arbitrage: Risk-Controlled Balancing of Competing Objectives in Language Models
William Overman, Mohsen Bayati
Modern language model deployments must often balance competing objectives, for example, helpfulness versus harmlessness, cost versus accuracy, and reward versus safety. We introduc…