GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
UKPLab
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
UKPLab
Model Tree
Base
Qwen/Qwen3-8B
Fine-tuned
this model
Input Modalities
Text
Output Modalities
Text
Supported Functionality
Dedicated Endpoints
Container
ProReviewer-8B is the backbone model for the ProReviewer agent, an R1-style reasoning agent that reviews scientific papers through structured investigation rather than passive generation. The model was trained with a multi-stage curriculum:
| Parameter | Value |
|---|---|
| Base model | Qwen/Qwen3-8B |
| Training method | SFT+ GRPO with step-level advantages |
| Training data | ICLR 2025 papers (UKPLab/ProReviewer-Dataset) |
| Architecture | Qwen3ForCausalLM |
| Parameters | 8B |
| Precision | bfloat16 |
bash
vllm serve UKPLab/ProReviewer-8B --max-model-len 32768 --dtype bfloat16
The recommended way to use this model is through the ProReviewer agent framework in the ProReviewer:
python
from reviewer.evaluation import run_inferencepaper = {"paper_id": "example","paper_content": "# Paper Title\n\nAbstract: ...","human_avg_score": 5.0,}# Option 1: Use a config name from config.toml (model served via vLLM)result = await run_inference(paper, model="proreviewer-8B")# Option 2: Use a local path (loads model directly via vLLM)result = await run_inference(paper, model="/path/to/ProReviewer-8B")
python
from transformers import AutoModelForCausalLM, AutoTokenizermodel = AutoModelForCausalLM.from_pretrained("UKPLab/ProReviewer-8B", torch_dtype="bfloat16")tokenizer = AutoTokenizer.from_pretrained("UKPLab/ProReviewer-8B")
bibtex
@article{fang2026passive,title={From Passive Generation to Investigation: A Proactive Scientific Peer Review Agent},author={Fang, Haishuo and Feng, Yue and Gurevych, Iryna},journal={arXiv preprint arXiv:2606.13349},year={2026}}
This model is released under the MIT License.