build1 distinct publisher
Agent Lightning v1.0 hands the RL loop to the harness, and the trainer gets text, not tokens
Microsoft reports Qwen3.5-9B going from 41.8% to 56.4% on SWE-bench Verified using 6K examples. The load-bearing change is who owns the agent loop, and what the service boundary costs.
Publishers:thenewstack.io
Reality
- Evidence32
- Adoption18
- Hype gap+28
- Incentives66