Xiangyuan Xue
xxyQwQ
AI & ML interests
LLM-based Agents & Multi-agent Systems & Agentic RL
Recent Activity
liked a model 9 days ago
tencent/Hy4-preview upvoted a paper about 1 month ago
JIT-Agent: Scaling Harness Intelligence via Just-in-Time Harness Evolution liked a model about 2 months ago
Qwen/Qwen3-4BOrganizations
models 17
xxyQwQ/train-ppo-sciworld-text-qwen2.5-7b
8B • Updated • 93
xxyQwQ/train-grpo-sciworld-text-qwen2.5-7b
8B • Updated • 121
xxyQwQ/train-strata-webshop-text-qwen2.5-3b-ultimate-version
3B • Updated • 7
xxyQwQ/train-strata-webshop-text-qwen2.5-3b-diverse-version
3B • Updated • 15
xxyQwQ/train-strata-webshop-text-qwen2.5-3b-judgment-version
3B • Updated • 5
xxyQwQ/train-strata-webshop-text-qwen2.5-3b-vanilla-version
3B • Updated • 4
xxyQwQ/train-strata-alfworld-text-qwen2.5-3b-diverse-version
3B • Updated • 5
xxyQwQ/train-strata-alfworld-text-qwen2.5-3b-judgment-version
3B • Updated • 6
xxyQwQ/train-strata-alfworld-text-qwen2.5-3b-ultimate-version
3B • Updated • 4
xxyQwQ/train-strata-alfworld-text-qwen2.5-3b-vanilla-version
3B • Updated • 8
datasets 0
None public yet