TokenRhythm/NeoHorse-1-9B

Name: TokenRhythm/NeoHorse-1-9B
Creator: TokenRhythm
License: apache-2.0

text-generationtransformersVerified checksumsagentictool-usecodingreasoninginstruction-followingtransformers

License: apache-2.0
Size: 17 GB
Revision: main
Downloads in the last 30 days: 0 / 30 days

Mirrored from TokenRhythm/NeoHorse-1-9B

All models by TokenRhythm →

NeoHorse-1-9B

Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness.

Technical Report

/* Reusable benchmark table architecture. Inline styles remain as a fallback for HF rendering. */ .vl-table { width: 100%; min-width: 100%; border-collapse: collapse; table-layout: fixed; font-size: 15px; } .vl-table th { font-size: 15px !important; line-height: 1.2; color: #c2410c; background: rgba(249,115,22,.10); } .vl-table td:not(.benchmark-cell):not([colspan]) { font-size: 15px; line-height: 1.2; vertical-align: middle; } .vl-table .benchmark-cell { padding: 12px 10px 12px 18px !important; vertical-align: middle; } .vl-table .benchmark-capability { font-size: 15px; font-weight: 600; line-height: 1.22; color: #c2410c; } .vl-table .benchmark-name { margin-top: 4px; font-size: 11px; font-weight: 400; line-height: 1.2; color: inherit; } .vl-table .metric-stack { display: flex; flex-direction: column; gap: 7px; padding: 3px 0; } .vl-table .metric-label { font-size: 10px; font-weight: 400; line-height: 1.1; color: inherit; } .vl-table .metric-value { margin-top: 2px; font-size: 15px; line-height: 1.15; color: inherit; } .model-table td:first-child { width: 34%; font-weight: 600; } /* HF's theme toggle sets the dark class on an ancestor. */ .dark .vl-table th, .dark .vl-table .benchmark-capability { color: #fdba74 !important; }

NeoHorse-1-9B is a 9B causal language model and an initial prototype on the path toward recursive self-improvement (RSI). It is post-trained from Qwen3.5-9B for text-based agent harnesses, tool use, coding, and instruction following.

Derived from Qwen/Qwen3.5-9B and fine-tuned by TokenRhythm. This release contains language-model weights only and is repackaged for text-only inference. Vision weights are not included. Repackaging changes configuration and tensor key names, without changing the fine-tuned tensor values.

Highlights

Path toward RSI: the routing harness assigns tasks to a heterogeneous model pool, records tool interactions and outcomes, estimates capability demand, and uses capability-level feedback to shape the next training mixture. Updated models can return to the harness, closing a prototype evaluation–selection–update loop; extending this loop across successive iterations is the next step toward RSI.
Agentic post-training framework: the associated research explores routing-guided curriculum SFT and routing-guided on-policy distillation to turn execution trajectories into training signal while preserving execution and harness context around each response.
Data quality: exact and near-duplicate removal, evaluation decontamination, structural validation, six-dimensional semantic evaluation, and subscene-level Scene/Goal/Outcome labeling.
Broad gains: 69.04 macro average across ten benchmarks versus 65.60 for Qwen3.5-9B (+3.44).

Model Details

Property	Value
Model family	NeoHorse Agent-Native Causal Language Model
Parameters	Approximately 9B
Base model	Qwen3.5-9B
Post-training	Routing-guided agentic post-training
Interface	Text input and text output
Context length	262,144 natively and extensible up to 1,010,000 tokens.
Weight format / precision	Safetensors / BF16

Evaluation

The 9B track compares NeoHorse-1-9B with five representative open-weight baselines: Granite-4.2-8B, Qwen3.5-9B, Ornith-1.5-9B, Gemma-4-12B-it, and Muse-Glimmer-30B. Results cover ten benchmarks and are grouped by capability. Higher is better; Δ is NeoHorse-1-9B minus Qwen3.5-9B. Bold and underline mark the best and second-best results in each benchmark row, respectively; ties share the same formatting.

Benchmark	Granite-4.2-8B	Qwen3.5-9B	Ornith-1.5-9B	Gemma-4-12B-it	Muse-Glimmer-30B	NeoHorse-1-9B	Δ vs Qwen3.5-9B
🤖 Agentic
QwenClawBench	37.01	44.04	47.27	43.53	46.11	48.73	+4.69
WorkBuddy Bench	35.07	39.60	29.29	29.65	45.85	40.15	+0.55
PinchBench	56.93	74.55	68.22	58.89	71.35	82.25	+7.70
VitaBench	23.00	31.25	26.75	36.50	48.50	42.25	+11.00
BFCL v4	52.06	64.88	65.03	62.06	53.74	67.43	+2.55
tau2-Bench	62.28	88.04	83.68	59.37	76.64	90.82	+2.78
💻 Coding
HumanEval	96.34	92.68	93.90	100.00	98.17	98.17	+5.49
LiveCodeBench v6	72.00	65.14	47.43	73.14	65.71	65.14	+0.00
📚 Instruction Following
IFBench	78.00	66.33	40.00	77.67	78.67	66.33	+0.00
IFEval	92.98	89.46	71.35	94.27	93.90	89.09	-0.37
📊 Overall
Ten-benchmark average	60.57	65.60	57.29	63.51	67.86	69.04	+3.44

Reported protocol: SGLang v0.5.17 · temperature=1.0 · top_p=0.95 · top_k=20 · min_p=0.0 · presence_penalty=1.5 · repetition_penalty=1.0 · thinking mode enabled with enable_thinking=true and force_nonempty_content=true. QwenClawBench, WorkBuddy Bench, and tau2-Bench use three runs; PinchBench and VitaBench use one run; the remaining benchmarks follow their official protocols. VitaBench uses the DeepSeek-V4-Flash simulator and judge.

Deployment

The examples below are for self-hosted deployment from a downloaded local checkpoint.

Local checkpoint path

The examples below assume the checkpoint has already been downloaded to local disk. Set MODEL_PATH to the directory containing config.json, tokenizer files, and model weights.

The OpenAI-compatible requests below use the server's --served-model-name (for example, neohorse-1-9b), not the filesystem path.

SGLang

The technical report uses SGLang v0.5.17.

bash

pip install "sglang==0.5.17"MODEL_PATH="/path/to/NeoHorse-1-9B"python3 -m sglang.launch_server \  --model-path "$MODEL_PATH" \  --served-model-name neohorse-1-9b \  --host 0.0.0.0 \  --port 30000 \  --context-length 262144 \  --reasoning-parser qwen3 \  --tool-call-parser qwen3_coder

Send an OpenAI-compatible request after the server starts:

bash

curl http://localhost:30000/v1/chat/completions \  -H 'Content-Type: application/json' \  -d '{"model":"neohorse-1-9b","messages":[{"role":"user","content":"Write a Python function that returns the first n Fibonacci numbers."}],"max_tokens":512}'

vLLM

bash

pip install -U vllmMODEL_PATH="/path/to/NeoHorse-1-9B"vllm serve "$MODEL_PATH" \  --served-model-name neohorse-1-9b \  --host 0.0.0.0 \  --port 8000 \  --max-model-len 262144 \  --reasoning-parser qwen3 \  --enable-auto-tool-choice \  --tool-call-parser qwen3_coder

The server exposes an OpenAI-compatible /v1/chat/completions endpoint. Send a request after the server starts:

bash

curl http://localhost:8000/v1/chat/completions \  -H 'Content-Type: application/json' \  -d '{"model":"neohorse-1-9b","messages":[{"role":"user","content":"Write a Python function that returns the first n Fibonacci numbers."}],"max_tokens":512}'

The example uses the configured 262,144-token context limit. Actual capacity depends on GPU memory and serving settings; reduce the context limit if needed.

License

NeoHorse-1-9B is released under the Apache License 2.0.

The upstream model is Qwen/Qwen3.5-9B. Its original copyright notice, Copyright 2026 Alibaba Cloud, is retained in the license file. TokenRhythm has modified the model through fine-tuning and repackaging for text-only inference. Modification notices are included in this model card and the released configuration, weight index, and Safetensors metadata.

Citation

@misc{neohorse2026,  title        = {NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness},  author       = {NeoHorse Team},  year         = {2026},  howpublished = {arXiv preprint},  eprint       = {2609.08183},  archivePrefix = {arXiv},  primaryClass = {cs.CL},  url          = {https://arxiv.org/abs/2609.08183}}

For questions or issue reports, use the NeoHorse project repository.