xxwu/Agent-STAR-SFT-3B
Text Generation • 3B • Updated • 24
Agent-STAR
Resources for paper "Demystifying Reinforcement Learning for Long-Horizon Tool-Using Agents: A Comprehensive Recipe"
-
-
xxwu/Agent-STAR-SFT-7B
Text Generation • 8B • Updated • 20 -
xxwu/Agent-STAR-SFT-1.5B
Text Generation • 2B • Updated • 15 -
xxwu/Agent-STAR-RL-3B
Text Generation • 3B • Updated • 298 -
xxwu/Agent-STAR-RL-7B
Text Generation • 8B • Updated • 287 • 1 -
xxwu/Agent-STAR-RL-1.5B
Text Generation • 2B • Updated • 297 -
xxwu/Agent-STAR-TravelDataset
Preview • Updated • 34 -
xxwu/Agent-STAR-TravelDatabase
Preview • Updated • 47 -
Demystifying Reinforcement Learning for Long-Horizon Tool-Using Agents: A Comprehensive Recipe
Paper • 2603.21972 • Published • 5