This release includes 1 breaking change for platform teams planning a safe upgrade.
Published 2mo
AI Agents & Assistants
✓ No known CVEs patched
✓ No known CVEs patched in this version
Topics
agent
agentic-ai
grpo
llms
lora
qwen
+3 more
qwen3
reinforcement-learning
rl
Summary
AI summaryRemoved beta KL divergence from training loss.
Full changelog
Release Highlights
What's Changed
- feat: Add W&B run config API (#615)
- feat: add tenant-scoped Tinker model aliases (#614)
- feat: Update Tinker renderers (#613)
- feat: Update Tinker renderers (#612)
- fix: Add pyarrow to Tinker extra (#611)
- build: Upgrade vLLM to 0.17.0 (#610)
- feat: Improved metrics in ART (#609)
- ci: Auto-build and upload uv cache on miss (#608)
- Remove beta KL divergence from training loss (#607)
- Fix ty type checker errors and warnings (#606)
- Clean up unused adapters before saving checkpoint (#605)
- build: Upgrade to unsloth 2026.3.3 (#604)
- Release v0.5.16 (#603)
- build: Downgrade unsloth and unsloth zoo (#602)
Full Changelog: https://github.com/OpenPipe/ART/compare/v0.5.16...v0.5.17
Breaking Changes
- Removed beta KL divergence from training loss
Weekly OSS security release digest.
The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.
No spam, unsubscribe anytime.
Share this release
About ART
Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.5, GPT-OSS, Llama, and more!
Related context
Related tools
Beta — feedback welcome: [email protected]