Resources for paper "Demystifying Reinforcement Learning for Long-Horizon Tool-Using Agents: A Comprehensive Recipe"
Xixi Wu
xxwu
AI & ML interests
None yet
Recent Activity
upvoted a paper about 14 hours ago
Marathoner: Ultra-Long-Horizon Autonomous Intelligence upvoted a paper 8 days ago
RRSI: Regularized Recursive Self-Improvement of Agent Harnesses upvoted a paper 5 months ago
Dynamic Skill Lifecycle Management for Agentic Reinforcement LearningOrganizations
None yet
models 9
xxwu/Agent-STAR-RL-7B-V2
8B • Updated • 16 • 1
xxwu/Agent-STAR-MacroRL-7B
8B • Updated • 9
xxwu/Agent-STAR-RL-1.5B
Text Generation • 2B • Updated • 33
xxwu/Agent-STAR-RL-7B
Text Generation • 8B • Updated • 25 • 1
xxwu/Agent-STAR-RL-3B
Text Generation • 3B • Updated • 30
xxwu/Agent-STAR-SFT-7B
Text Generation • 8B • Updated • 24
xxwu/Agent-STAR-SFT-3B
Text Generation • 3B • Updated • 22
xxwu/Agent-STAR-SFT-1.5B
Text Generation • 2B • Updated • 30
xxwu/MoLoRAG-QwenVL-3B
Visual Document Retrieval • 4B • Updated • 48 • 2