---
library_name: transformers
pipeline_tag: text-generation
base_model: Chenyu-Zhou/StepORLM-Qwen3-8B
tags:
  - solid-opt
  - operations-research
  - mathematical-optimization
  - self-distillation
  - grpo
  - qwen3
---

# SOLID-StepORLM

This is the checkpoint of **SOLID (Solver-Informed Self-Distillation)** built from `Chenyu-Zhou/StepORLM-Qwen3-8B` for operations-research modeling and solver-backed answer generation.

The model was trained with GRPO and solver-informed token-level KL supervision. It uses the COPT-style StepORLM response template.

## Evaluation

Each problem was sampled 64 times. `maj@64` is majority-vote accuracy; `pass@k` uses the unbiased pass-at-k estimator. 

| Dataset | maj@64 | pass@1 | pass@2 | pass@4 |
|---|---:|---:|---:|---:|
| OptMATH | 31.33 | 18.25 | 24.40 | 30.28 |
| MAMO-Complex | 70.44 | 66.43 | 71.58 | 74.79 |
| InOR | 48.00 | 39.81 | 46.07 | 50.59 |



## Usage

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "AIOR-Research/SOLID-StepORLM"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype="auto",
    device_map="auto",
)
```

The generated optimization code expects a compatible COPT environment for execution.

## Citation

If you use SOLID in your research, please cite:

```bibtex
@misc{zhu2026verifiedanswerssolverinformedselfdistillation,
      title={Beyond Verified Answers: Solver-Informed Self-Distillation for Bootstrapping Operations Research Language Models},
      author={Rui Zhu and Minglong Cao and Chenyu Zhou and Jianghao Lin and Dongdong Ge},
      year={2026},
      eprint={2609.09957},
      archivePrefix={arXiv},
      primaryClass={math.OC},
      url={https://arxiv.org/abs/2609.09957},
}
```