Microsoft's FrogNano: 4B coding agent trained with pure RL, no frontier distillation
dair_ai · x · 2026-09-09
A new Microsoft report (highlighted by dairai) shows competitive small coding agents can be built without any distillation from frontier models. FrogNano is a 4B coding agent post-trained purely with RL on 1,500 software engineering environments. The key ingredient is online task synthesis: the pipeline generates tasks calibrated to the frontier of learnability of the current checkpoint, so the agent always trains on problems it can just barely solve — calibration matters more than volume. The target is an agent that runs on minimal machines, ruling out both frontier backbones and teachers.
More from coding & agent
- One prompt, full Blender animation: dev says he never touched Blender once — iamfakhrealam · 2026-10-26
- Claude Code finds root backdoor in Honda Civic head unit, then debloats it — IndraVahan · 2026-10-26
- Claude Code + Monid MCP builds a $12K/year B2B prospecting engine on live data — aryanXmahajan · 2026-10-26
- Karpathy shares CLAUDE.md rulebook to stop AI coding agents from piling up tech debt — mdancho84 · 2026-10-26
- Rethinking dependencies in the agent era: drop libs that save 20 lines of code — gethackteam · 2026-10-26
- RustGIS hits 2,000 GitHub stars in two weeks with agent-first architecture — giswqs · 2026-10-26