-
AgentSafeEvo: Adversarial Co-Evolution for LLM Agent Safety
Paper • 2610.19422 • Published • 7 -
lalalamdbf/AgentSafeEvo-Defender-Qwen3-8B
Text Generation • 8B • Updated • 212 -
lalalamdbf/AgentSafeEvo-Attacker-Qwen3-8B-SFT
Text Generation • 8B • Updated • 197 -
lalalamdbf/AgentSafeEvo-Attacker-Qwen3-8B-RL
Text Generation • 8B • Updated • 188
👋 Open to Work
Xiaoyu Wen
XiaoyuWen
AI & ML interests
None yet
Recent Activity
upvoted a collection 9 days ago
REX authored a paper 13 days ago
JailbreakSkill: Scaling Automated Red-Teaming with Reusable and Ever-Evolving SkillsOrganizations
-
AgentSafeEvo: Adversarial Co-Evolution for LLM Agent Safety
Paper • 2610.19422 • Published • 7 -
lalalamdbf/AgentSafeEvo-Defender-Qwen3-8B
Text Generation • 8B • Updated • 212 -
lalalamdbf/AgentSafeEvo-Attacker-Qwen3-8B-SFT
Text Generation • 8B • Updated • 197 -
lalalamdbf/AgentSafeEvo-Attacker-Qwen3-8B-RL
Text Generation • 8B • Updated • 188
Paper: "Not All Turns Matter: Credit Assignment for Multi-Turn Jailbreaking."
models 10
XiaoyuWen/MAGIC-attacker-sft-Qwen2.5-14B-Instruct
15B • Updated • 7
XiaoyuWen/MAGIC-attacker-sft-Qwen2.5-7B-Instruct
8B • Updated • 17
XiaoyuWen/MAGIC-attacker-sft-Llama3.1-8B-Instruct
8B • Updated • 9
XiaoyuWen/TRACE-Mix-Qwen2.5-3B-Instruct
Text Generation • 3B • Updated • 836 • 2
XiaoyuWen/TRACE
Reinforcement Learning • Updated
XiaoyuWen/PIA
Updated
XiaoyuWen/MAGIC
Text Generation • Updated • 1
XiaoyuWen/MAGIC-Llama3.1-8B-Instruct
Text Generation • Updated • 98
XiaoyuWen/MAGIC-Qwen2.5-7B-Instruct
Text Generation • 8B • Updated • 51 • • 2
XiaoyuWen/MAGIC-Qwen2.5-14B-Instruct
Text Generation • Updated • 59 • 2