Xiangyuan Xue
xxyQwQ
AI & ML interests
LLM-Based Agents, Multi-Agent Systems, Reinforcement Learning
Recent Activity
upvoted
a
paper
1 day ago
AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Security
upvoted
a
paper
about 1 month ago
Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows
authored
a paper
4 months ago
CoMAS: Co-Evolving Multi-Agent Systems via Interaction Rewards
Organizations
