NeoHorse-1 paper proposes recursive self-improvement via agentic post-training

_akhaliq · x · 2026-09-10

The TokenRhythm team released the NeoHorse-1 paper on Hugging Face, "Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness," alongside an HF model collection and a GitHub repo. The approach uses agent-style post-training with a routing harness to let models improve themselves iteratively. The method is novel and not yet widely validated.

Related event: NeoHorse-1 Paper Proposes Recursive Self-Improvement via Agentic Post-Training(2 posts)→

Original post →

More from Research

Research channel →