AINeutralarXiv – CS AI · 8h ago6/10
🧠
Calibration Is Not Control: Why LLM-Agent Oversight Needs Intervention
Researchers argue that current LLM agent oversight systems rely on flawed scalar risk prediction rather than intervention-aware decision-making. Their framework measures intervention advantage—the actual utility gain from intervening—and demonstrates that action-conditioned control significantly outperforms traditional calibrated risk scoring across multiple benchmarks.