AOI adds keyframe capture, volume-gated audio transcription, and visual narration to computer-use agents, producing +17 to +48 pp gains over screenshot baselines on DynaCU-Bench with no retraining.
Towards trustworthy agentic IoEV: AI agents for explainable cy- berthreat mitigation and state analytics
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
AgentSOC introduces a multi-layer agentic AI architecture for SOC automation that handles alert correlation, anticipatory reasoning, and risk-balanced response selection, shown feasible via conceptual enterprise evaluation and a LANL data POC.
citing papers explorer
-
Agent-Computer Observation Interfaces Enable Dynamic Computer Use
AOI adds keyframe capture, volume-gated audio transcription, and visual narration to computer-use agents, producing +17 to +48 pp gains over screenshot baselines on DynaCU-Bench with no retraining.
-
AgentSOC: A Multi-Layer Agentic AI Framework for Security Operations Automation
AgentSOC introduces a multi-layer agentic AI architecture for SOC automation that handles alert correlation, anticipatory reasoning, and risk-balanced response selection, shown feasible via conceptual enterprise evaluation and a LANL data POC.