Agentic training for agentic work.
Post-training includes reinforcement learning inside agent harnesses such as @openclaw, Hermes Agent by @NousResearch, @pidotdev, and @opencode. The model learns through tool calls and multi-turn tasks.
4/
Liquid AI says post-training runs reinforcement learning inside agent harnesses
AISummary
Liquid AI says its post-training includes reinforcement learning inside agent harnesses such as OpenClaw, Hermes Agent by Nous Research, pi, and opencode. The model learns from tool calls and multi-turn tasks in those environments.
Post on XView on X
Source: Liquid AI · x.comPublished · added here