3 citations · 3 across the 8 of their papers we have counts for
Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
Alignment in Time: Peak-Aware Orchestration for Long-Horizon Agentic Systems
Hanjing Shi, Dominic DiFranzo
Traditional AI alignment primarily focuses on individual model outputs; however, autonomous agents in long-horizon workflows require sustained reliability across entire interaction…
cs.AI2026
Human Control Is the Anchor, Not the Answer: Early Divergence of Oversight in Agentic AI Communities
Hanjing Shi, Dominic DiFranzo
Oversight for agentic AI is often discussed as a single goal ("human control"), yet early adoption may produce role-specific expectations. We present a comparative analysis of two…