3 papers
cs.AI2026
AgentRiskBOM: A Risk-Scoping Security Bill of Materials for Agentic AI Systems
Srimonti Dutta, Akshata Kishore Moharir
Agentic AI systems retrieve private context, invoke tools, write files, call external services, coordinate with other agents, and may act without human approval. Existing bill of m…
cs.AI2026
Mental Health AI Safety Claims Must Preserve Temporal Evidence
Srimonti Dutta, Ratna Kandala
The safety of mental health AI is often judged at the wrong temporal scale. Current evaluations typically score isolated responses, endpoint outcomes, or aggregate dialogue quality…
cs.AI2026
Stability vs. Manipulability: Evaluating Robustness Under Post-Decision Interaction in LLM Judges
Srimonti Dutta, Akshata Kishore Moharir
LLM-as-judge evaluation is widely used in benchmarking pipelines, where model outputs are compared and ranked using automated evaluators. These pipelines typically assume that judg…