Microsoft open-sources Agent Lightning v1.0 agentic RL framework
What happened
On 8 October 2026, Microsoft Research open-sourced Agent Lightning v1.0, a lightweight agentic reinforcement learning framework of about 3,500 lines of code. The framework was rebuilt around the Harnessed Agentic RL paradigm, letting the agent harness used at deployment take part directly in training without reimplementing the agent inside the training framework. The only public information so far comes from this single first-hand report by Microsoft Research; it does not mention earlier versions, a release timeline or comparisons with other frameworks, and further details will have to wait for more coverage.
Written by AI from the reports · updated 9 d ago
Timeline
Follow the reports to see the event from each side.
- Microsoft ResearchSelectedAgent Lightning v1.0: A 3,500-Line Lightweight Agentic RL Framework for Training Agents with Real Harnesses
Training AI agents with reinforcement learning can be challenging because their tools, context, and decision-making are managed by complex frameworks. Agent Lightning connects existing agents to RL training, making it easier to improve them without rebuilding them.
Heat of this event
Current heat 3·Peak in the comparable range 3（Oct 9 17:00）·Change over 24 hours in the comparable range –
The trend compares only the same accounts observed without a break, so its range can be narrower than the current heat count. Move the pointer or tap the chart to see each hour; with a keyboard, use the left and right arrow keys.