Danau5tin/Orca-Agent-RL

Qwen3-14B Orchestrator Agent Reinforcement Learning. **Achieved 160% improvement** on Stanford's TerminalBench

2 best points · 1 comments · 1 Hacker News post · 104 GitHub stars · View on GitHub

Hacker News discussions

• Scaling Coding-Agent RL to 32x H100s. 160% Improvement on Stanford's TBench (2 points, 1 comments, by Danau5tin, 2025-11-03)