CodeScout RL-trained code search agents (1.7B, 4B, 14B) that outperform 2–18× larger models using only a Unix terminal. 📄 arxiv.org/abs/2603.17829 OpenHands/CodeScout-14B Text Generation • 15B • Updated 1 day ago • 76 • 1 OpenHands/CodeScout-4B Text Generation • 4B • Updated 1 day ago • 80 OpenHands/CodeScout-1.7B Text Generation • 2B • Updated 1 day ago • 78 OpenHands/CodeScout-1.7B-RFT Text Generation • 2B • Updated 1 day ago • 77 • 1
CodeScout RL-trained code search agents (1.7B, 4B, 14B) that outperform 2–18× larger models using only a Unix terminal. 📄 arxiv.org/abs/2603.17829 OpenHands/CodeScout-14B Text Generation • 15B • Updated 1 day ago • 76 • 1 OpenHands/CodeScout-4B Text Generation • 4B • Updated 1 day ago • 80 OpenHands/CodeScout-1.7B Text Generation • 2B • Updated 1 day ago • 78 OpenHands/CodeScout-1.7B-RFT Text Generation • 2B • Updated 1 day ago • 77 • 1