VPR-Qwen3-4B-Sudoku

This is a Qwen3-4B checkpoint trained with Verifiable Process Rewards (VPR) on Markovian Sudoku interactions. At each visited state, VPR samples four action responses, scores their parsed actions with a task-grounded constraint-based Sudoku oracle, commits one highest-reward candidate, and optimizes all eligible candidates using locally normalized advantages.

Reported result

Evaluation SR CR
Sudoku 80.60 ยฑ 4.16 84.22 ยฑ 3.15

Values are percentages reported under the evaluation protocol in the VPR paper. SR is success rate; CR is completion rate.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "nics-efc/VPR-Qwen3-4B-Sudoku"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype="auto",
    device_map="auto",
)

inputs = tokenizer("<current Markovian game prompt>", return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=512)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Use the environment prompts, parsers, and action conventions in the VPR codebase for reproduction. These task-specific checkpoints are not intended as general-purpose assistants.

Resources

Limitations

Training relies on task-grounded oracle signals and specific Markovian prompts. Performance outside the documented environments and action formats has not been established. Evaluate safety and correctness before open-ended deployment.

Citation

@misc{yuan2026verifiable,
  title         = {Verifiable Process Rewards for Agentic Reasoning},
  author        = {Huining Yuan and Zelai Xu and Huaijie Wang and Xiangmin Yi and Jiaxuan Gao and Xiao-Ping Zhang and Yu Wang and Chao Yu and Yi Wu},
  year          = {2026},
  eprint        = {2605.10325},
  archivePrefix = {arXiv},
  primaryClass  = {cs.AI},
  url           = {https://arxiv.org/abs/2605.10325}
}
Downloads last month
17
Safetensors
Model size
4B params
Tensor type
BF16
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for nics-efc/VPR-Qwen3-4B-Sudoku

Finetuned
Qwen/Qwen3-4B
Finetuned
(1,278)
this model

Collection including nics-efc/VPR-Qwen3-4B-Sudoku

Paper for nics-efc/VPR-Qwen3-4B-Sudoku