arxiv:2512.14051
Mengyuan Sun
blue01223
AI & ML interests
AI Security, LLM
Recent Activity
upvoted
a
paper
about 12 hours ago
ToolSafe: Enhancing Tool Invocation Safety of LLM-based agents via Proactive Step-level Guardrail and Feedback
authored
a paper
22 days ago
OpenDataArena: A Fair and Open Arena for Benchmarking Post-Training Dataset Value
upvoted
a
paper
24 days ago
OpenDataArena: A Fair and Open Arena for Benchmarking Post-Training Dataset Value
Organizations
