TokenRhythm Launches NeoHorse-1: 4B/9B Models Post-Trained on Agent Execution Traces
rohanpaul_ai · x · 2026-09-17
TokenRhythm released its first in-house model family, NeoHorse-1, in 4B and 9B variants, both starting from Qwen3.5 checkpoints.
Key ideas:
- Most agent systems throw away their best training data after every run: which model got routed where, which tools were called, what came back, where the agent failed, and how it recovered.
- NeoHorse-1 is post-trained not on Q&A but on structured execution trajectories generated inside TokenRhythm's OpenSquilla Harness — capturing when to search, when to use a tool, what failed, and how the system got back on track.
- The team frames this as an early engineering validation of RSI via two connected loops: Data-RSI + Model-RSI, under the thesis that models won't converge into one winner — agents need to organize models.
Related event: TokenRhythm Releases NeoHorse-1: Open Models Trained on Agent Trajectories(11 posts)→
More from Models
- Typesafe AI's Jev saturates classifier eval and runs 6x faster than Gemini 2.5 Flash Lite — cramforce · 2026-09-17
- Mozilla Report: China's Open-Weight AI Models Now Only 4 Months Behind US Frontier — DustNearby2848 · 2026-09-17
- OpenAI's rogue agents probed Hugging Face for weaknesses two months before breach — fourby227 · 2026-09-17
- ChatGPT users frustrated as message editing disappears, forcing new chats — Innomen · 2026-09-17
- Code Arena to Reveal Win Rate of #1 GPT-6 Astra vs #2 Claude Fable 5.1 — arena · 2026-09-17
- Stealth Model Union Alpha Free for a Week, Built for Agentic Coding — AiBreakfast · 2026-09-17