2 papers
cs.CR2026
Design Principles for the Construction of a Benchmark Evaluating Security Operation Capabilities of Multi-agent AI Systems
Yicheng Cai, Mitchell John DeStefano, Guodong Dong +5
As Large Language Models (LLMs) and multi-agent AI systems are demonstrating increasing potential in cybersecurity operations, organizations, policymakers, model providers, and res…
cs.HC2026
Seeing Eye to Eye: Enabling Cognitive Alignment Through Shared First-Person Perspective in Human-AI Collaboration
Zhuyu Teng, Pei Chen, Yichen Cai +5
Despite advances in multimodal AI, current vision-based assistants often remain inefficient in collaborative tasks. We identify two key gulfs: a communication gulf, where users mus…