Microsoft open-sources Agent Lightning for non-intrusive RL training of agents
thisdudelikesAI · x · 2026-08-15
Microsoft open-sourced Agent Lightning (17k+ stars), featuring a decoupled design where the agent runtime and training loop never touch each other. Agents running on LangChain, AutoGen, or plain Python emit spans to a shared store, allowing the trainer to read data and perform RL training externally without rewriting the agent code or binding to a specific framework.
More from coding & agent
- Coding agents keep opening 3 stacked PRs per chat, and merging them is a nightmare — holdenmatt · 2026-10-16
- Google-led paper uses sequential auctions to organize decentralized LLM agent workflows — _onionesque · 2026-10-16
- Since OpenAI's math release, GitHub contributors keep driving down the integer-multiplication kappa — xennygrimmato_ · 2026-10-16
- Pattern MCP makes coding agents check existing components before writing new code — DonR954 · 2026-10-16
- Zero-keyframe procedural spider walks walls and ceilings using pure raycasts — yshan2u · 2026-10-16
- OpenCode v1.19.2 keeps 1.x installs off the 2.x update path — opencode-agent[bot] · 2026-10-16