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 Mar 19 • 104 • 2 OpenHands/CodeScout-4B Text Generation • 4B • Updated Mar 19 • 101 • • 1 OpenHands/CodeScout-1.7B Text Generation • 2B • Updated Mar 19 • 392 • • 1 OpenHands/CodeScout-1.7B-RFT Text Generation • 2B • Updated Mar 19 • 56 • • 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 Mar 19 • 104 • 2 OpenHands/CodeScout-4B Text Generation • 4B • Updated Mar 19 • 101 • • 1 OpenHands/CodeScout-1.7B Text Generation • 2B • Updated Mar 19 • 392 • • 1 OpenHands/CodeScout-1.7B-RFT Text Generation • 2B • Updated Mar 19 • 56 • • 1
