NeoHorse-1 Paper Proposes Recursive Self-Improvement via Agentic Post-Training

The TokenRhythm team released NeoHorse-1 on Hugging Face, proposing recursive self-improvement through agentic post-training that combines intelligent routing, structured feedback loops, and curriculum-based distillation.

2026-09-09 ~ 2026-09-10 · 2 related posts

• NeoHorse-1: Recursive self-improvement via agentic post-training with routing harness — TokenRhythm · 2026-09-09
• NeoHorse-1 paper proposes recursive self-improvement via agentic post-training — _akhaliq · 2026-09-10