AI & Enterprise
Microsoft releases Agent Lightning v1.0 agent reinforcement learning framework
Microsoft has released its agent reinforcement learning framework, Agent Lightning v1.0, on GitHub. The framework centers on a production harness that handles context building, tool execution and the agent-environment interaction loop, while the training engine observes only LLM Q&A logs. Microsoft said it used 6,000 training examples to train a Qwen3.5-9B model and raised its SWE-Bench Verified score to 56.4 from 41.8. Researchers cited benefits and cautioned about reward design and infrastructure needs.
