Microsoft releases Agent Lightning 1.0: SI agents are trained with reinforcement learning in their real harness
Prepared by Sintelligent with the help of SI. Published in SI: . Updated: .
Agents can be fine-tuned on their real work without being rebuilt for the lab.
Microsoft Research released Agent Lightning v1.0, a compact (about 3,500 lines) framework for training agents with reinforcement learning in which the agent runs in its real harness and talks to the model through a proxy instead of being rewritten for the training system. According to Microsoft, training lifted Qwen3.5-9B from 41.8% to 56.4% on SWE-bench Verified (+14.6 points) using about 6,000 examples and sped up the end-to-end process about twofold compared with synchronous training.
Sources 1