AI Briefing#agentic-rl
The latest AI and developer news about #agentic-rl, with the original source and a short summary.
The latest AI and developer news about #agentic-rl, with the original source and a short summary.
The 300B-scale model achieves 46.2% on Terminal-Bench 4.0 using only 64 NVIDIA B300 GPUs over five days.
Microsoft Research Asia released Agent Lightning v1.0, a 3,500-line framework that raised Qwen3.5-9B's Pass@1 on SWE-bench Verified by 14.6 percentage points using only 6,000 training samples.
Agent Lightning v1.0 has been released as an RL training framework leveraging agent harnesses.
The reinforcement learning-based CUDA Agent has demonstrated superior CUDA kernel generation performance compared to existing models.
When training agentic RL, you must avoid token mismatch issues that arise from re-encoding decoded tokens.
MDLM improved agentic RL performance as a stronger text-based world model than AR.
It covers the technical challenges and solutions involved in applying Agentic RL to the GPT-OSS model to optimize agent performance.