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.
models 10
OpenHands/CodeScout-1.7B-RFT
Text Generation • 2B • Updated • 23 • • 1
OpenHands/CodeScout-1.7B
Text Generation • 2B • Updated • 111 • • 1
OpenHands/CodeScout-4B
Text Generation • 4B • Updated • 548 • • 1
OpenHands/CodeScout-14B
Text Generation • 15B • Updated • 141 • • 4
OpenHands/openhands-critic-4b-v1.0
Text Classification • 4B • Updated • 97 • 8
OpenHands/openhands-critic-32b-exp-20250417
Token Classification • 32B • Updated • 38 • 21
OpenHands/openhands-lm-32b-v0.1
Text Generation • 33B • Updated • 85 • 392
OpenHands/openhands-lm-7b-v0.1
Text Generation • 8B • Updated • 58 • 82
OpenHands/openhands-lm-1.5b-v0.1
Text Generation • 2B • Updated • 12.2k • 13
OpenHands/openhands-lm-32b-v0.1-ep3
Text Generation • 33B • Updated • 15 • 4
datasets 11
OpenHands/openhands-index
Viewer • Updated • 40.7k • 130 • 1
OpenHands/SWE-bench_Pro-locagent
Viewer • Updated • 264 • 133
OpenHands/SWE-bench_Lite-locagent
Viewer • Updated • 300 • 32
OpenHands/SWE-bench_Verified-locagent
Viewer • Updated • 500 • 337
OpenHands/SWE-rebench-code-search
Viewer • Updated • 17.6k • 785
OpenHands/SWE-Gym-code-search
Viewer • Updated • 2.32k • 220
OpenHands/SWE-smith-py-code-search
Viewer • Updated • 39.3k • 266
OpenHands/CodeScout_Training_Rollouts
Viewer • Updated • 54.8k • 82 • 2
OpenHands/CodeScout_Eval_Rollouts
Viewer • Updated • 12.7k • 190
OpenHands/openhands-evaluation-outputs
Updated • 384 • 1