AI.info

Wei Ye

Explore Wei Ye on AI.info.

• ToolSafe: Enhancing Tool Invocation Safety of LLM-based agents via Proactive Step-level Guardrail and Feedback
• Modeling Uncertainty Trends for Timely Retrieval in Dynamic RAG
• OSWorld-MCP: Benchmarking MCP Tool Invocation In Computer-Use Agents
• Preference-driven Knowledge Distillation for Few-shot Node Classification