NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness
NeoHorse-1 introduces agentic post-training with intelligent routing that lifts agent benchmark scores at 4B and 9B scales, prototyping recursive self-improvement.
NeoHorse-1 is a family of agent-native models trained through agentic post-training: routing-harness logs (predicted capability demand, service tier, interaction) become structurally validated training data organized into a three-stage SFT curriculum plus routing-guided on-policy distillation. Capability-guided allocation converts evaluation feedback into the next training mixture, closing an evaluation-selection-update loop. Post-training raises the macro-average from 58.94 to 64.87 at 4B and from 65.60 to 69.04 at 9B across eleven agent, tool-use, coding, and instruction-following benchmarks. The authors position it as a prototype of harness-mediated recursive self-improvement.
- Routing-harness logs become validated training data preserving reasoning, tool calls, and context
- Three-stage SFT curriculum plus routing-guided on-policy distillation under one capability progression
- Macro-average improves 58.94 to 64.87 at 4B and 65.60 to 69.04 at 9B across 11 benchmarks
- Framed as an initial prototype of harness-mediated recursive self-improvement
- Tags
- agentic-post-trainingbenchmarksfine-tuningmodel-routingon-policy-distillationrecursive-self-improvementtool-use
- AI models
- NeoHorse-1
From the original article
1 min read at huggingface.co
Recursive self-improvement (RSI) requires a concrete mechanism through which an AI system observes its capabilities and converts that evidence into the next round of learning. We present NeoHorse-1, a family of agent-native models developed to explore this path through agentic post-training.
By NeoHorse Team, Guoliang Cao, Guohao Dai · huggingface.co
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.