Meta researchers taught an 8B AI model to match Claude Opus 4.5 — without the frontier price tag

RL, enhancing AI agent efficiency in complex workflows by teaching optimal harness use, improving success rates.
InfoQ

Embabel Agent Framework Reaches 1.0

Unlock the full InfoQ experience by logging in! Stay updated with your favorite authors and topics, engage with content, and download exclusive resources. Kasia Trapszo discusses how Netflix evolved ...