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
AI & ML interests
None defined yet.
Recent Activity
models 10
OpenHands/CodeScout-1.7B-RFT
Text Generation • 2B • Updated • 37 • • 1
OpenHands/CodeScout-1.7B
Text Generation • 2B • Updated • 238 • • 1
OpenHands/CodeScout-4B
Text Generation • 4B • Updated • 65 • • 1
OpenHands/CodeScout-14B
Text Generation • 15B • Updated • 107 • • 2
OpenHands/openhands-critic-4b-v1.0
Text Classification • 4B • Updated • 24 • 8
OpenHands/openhands-critic-32b-exp-20250417
Token Classification • 32B • Updated • 72 • 21
OpenHands/openhands-lm-32b-v0.1
Text Generation • 33B • Updated • 117 • 391
OpenHands/openhands-lm-7b-v0.1
Text Generation • 8B • Updated • 102 • 82
OpenHands/openhands-lm-1.5b-v0.1
Text Generation • 2B • Updated • 45 • 12
OpenHands/openhands-lm-32b-v0.1-ep3
Text Generation • 33B • Updated • 6 • 4
datasets 10
OpenHands/SWE-bench_Pro-locagent
Viewer • Updated • 264 • 10
OpenHands/SWE-bench_Lite-locagent
Viewer • Updated • 300 • 15
OpenHands/SWE-bench_Verified-locagent
Viewer • Updated • 500 • 121
OpenHands/SWE-rebench-code-search
Viewer • Updated • 17.6k • 28
OpenHands/SWE-Gym-code-search
Viewer • Updated • 2.32k • 46
OpenHands/SWE-smith-py-code-search
Viewer • Updated • 39.3k • 33
OpenHands/CodeScout_Training_Rollouts
Viewer • Updated • 54.8k • 68 • 2
OpenHands/CodeScout_Eval_Rollouts
Viewer • Updated • 12.7k • 79
OpenHands/openhands-evaluation-outputs
Updated • 79 • 1
OpenHands/openhands-feedback
Viewer • Updated • 275 • 112 • 6