Microsoft's Agent Lightning Boosts Coding AI 14.6 Points Without Rebuilding Agents
Microsoft Research open-sourced a 3,500-line RL framework that trains agents using their real deployment harnesses, boosting Qwen3.5-9B by 14.6 points on SWE-bench.
Source
Microsoft Research
Published
Author
AlphaSignal Newsroom
Read
1 min read
Microsoft Research open-sourced a 3,500-line RL framework that trains agents using their real deployment harnesses, boosting Qwen3.5-9B by 14.6 points on SWE-bench.
Reporting is indexed from AlphaSignal. Rights remain with the original publisher and cited sources.
