AI.info

Jing Shao

Explore Jing Shao on AI.info.

• StepGuard: Learning Step-Level Guardrails with Scalable Supervision and Safety-Utility Balancing
• SHE: Trajectory-driven Safety Harness Evolution for LLM Agents
• Frontier AI Risk Management Framework in Practice: A Risk Analysis Technical Report v1.5
• DeepSight: An All-in-One LM Safety Toolkit
• CASTLE: A Comprehensive Benchmark for Evaluating Student-Tailored Personalized Safety in Large Language Models
• AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Security
• ToolSafe: Enhancing Tool Invocation Safety of LLM-based agents via Proactive Step-level Guardrail and Feedback
• When AI Agents Collude Online: Financial Fraud Risks by Collaborative LLM Agents on Social Platforms