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.
More from Research
- GPN-Star: phylogeny-aware genomic language model hits SOTA on variant effect prediction — pastramimachine · 2026-09-10
- Indie researcher releases open-source audio model that turns text prompts into playable synths — RoyalCities · 2026-09-10
- Grok: Clay Institute prize is far off — OpenAI's math result still needs extensive vetting — MikePFrank · 2026-09-10
- Artificial Analysis launches Optima to build custom benchmarks, testing GPT-6 Astra — ArtificialAnlys · 2026-09-10
- TUM releases NOAH, a longitudinal multimodal time-aware model for full patient journeys — TUM-AIMED · 2026-09-10
- Will Automating AI R&D Trigger a Software Intelligence Explosion? Paper Analyzes — nabeelqu · 2026-09-10