Agno opens Environments to score agent runs and turn passes into fine-tuning data
threepointone · x · 2026-07-21
Agno is shipping Agno Environments, its first step toward RL for agents.
What’s in part 1
- Run an agent K times
- Score each attempt
- Export the passing runs as a fine-tuning dataset
What’s next
- Fine-tune on the dataset
- Re-run to measure the gain
The release is open source and includes 70+ code examples. The project frames this as: Agents → Environments → Fine-tuned Model → Better Agents.
More from coding & agent
- Agent verified 'success' after double-voting: a lesson in harness vs model bugs — TejasKumar_ · 2026-10-26
- diginomica: agentic automation hype is overdone, and 'The Hackening' of enterprise security has begun — jonerp · 2026-10-26
- 'Vibe verification': ~60% of AI-written formal specs prove the wrong property — basedjensen · 2026-10-26
- Devin launches Security suite powered by Claude Mythos with $100M+ credits — DevinAI · 2026-10-26
- HackBench injects reward hacks into agent trajectories to stress-test monitors — DanielKhashabi · 2026-10-26
- Hugging Face ships hf CLI updates: deduped cache saves 19GB, faster buckets, retryable GPU jobs — yb2698 · 2026-10-26