Agent Lightning trains agents through their existing harness
Agent Lightning trains agents through their existing harness
Microsoft Research's October 7 technical overview describes the rebuilt Agent Lightning v1.0: roughly 3,500 lines of control-plane code, agents running as Kubernetes jobs, and an LLM proxy that lets an existing harness participate in reinforcement learning. Its reported Qwen3.5-9B coding pipeline improved SWE-bench Verified Pass@1 from 41.8% to 56.4% using about 6,000 samples.
Editorial takeaway: the training setup should resemble the deployed agent. Inspect the released workflow before adopting it; those results describe the authors' coding experiment, and running training still requires compute and infrastructure. This is a technical overview, not a claim that the framework first launched today.
Source: Microsoft Research · microsoft.com