TokenRhythm/NeoHorse

NeoHorse Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness. NeoHorse-Jev · NeoHorse-1 NeoHorse is TokenRhythm's family of open-weight models for agent workflows. NeoHorse-1 provides 4B and 9B language models for tool use, coding, and instruction following. NeoHorse-Jev builds on NeoHorse-1-4B to make structured decisions through prefill-only inference. Deployment NeoHorse-Jev-4B turns application state into decisions and probabilities. Built on NeoHorse-1-4B, it uses prefill-only inference to select an action with Choice, check a condition with Noul, or assign a rating with Score. Applications define the questions and possible answers, then use the results to route requests, select tools, or control a workflow. In our evaluation, it scores 77.70 across six text benchmark groups, the highest among the four open-weight decision models with complete results in the comparison. Across Nimble, VitaminC, and MASSIVE, it reaches 83.26% mean accuracy, 11.50 percentage points above NeoHorse-1-4B. See the full comparison and evaluation protocols. Scores are…