DR-Venus：基于开放数据的边缘级深度研究智能体

DR-Venus is a 4B-parameter deep research agent trained entirely on open data. It establishes a new small-model frontier on multiple deep research benchmarks, demonstrating that strong agentic capabilities can emerge from careful data curation and effective training strategies at edge scale.

Figure 1: Overview of the DR-Venus training pipeline.

🔥 News

• 2026-04-24   Released model checkpoints of GGUF version: DR-Venus-4B-SFT-GGUF and DR-Venus-4B-RL-GGUF.
• 2026-04-23   Our technical report is now available on arXiv and HF Daily Paper (#3 Paper of the day).
• 2026-04-22   Released model checkpoints: DR-Venus-4B-SFT and DR-Venus-4B-RL.
• 2026-04-22   Open-sourced the full training and inference codebase.

📖 Overview

The core goal of DR-Venus is to build a strong edge-scale deep research agent under limited open-data supervision by improving both data quality and effective data utilization. The project consists of three stages:

📊 Main Results

DR-Venus-4B establishes a strong small-model frontier on multiple deep research benchmarks.

Comparison with Small Open Models

Key takeaways:

• DR-Venus-4B-SFT already outperforms prior small open agents on most tracked benchmarks.
• DR-Venus-4B-RL further improves over SFT by +2.3 on BrowseComp and +2.0 on BrowseComp-ZH.
• RL mainly improves long-horizon execution reliability, formatting stability, and tool-use calibration.

Figure 2: Pass@K comparison on BrowseComp and BrowseComp-ZH.

📦 Data Pipeline

The SFT pipeline is built from open REDSearcher trajectories and focuses on making limited supervision more useful for a small model.

Raw REDSearcher Trajectories (10,001)
  │
  ├── Structural Cleaning    ── environment alignment, tool normalization,
  │                              disallowed-tool pruning, duplicate removal
  ├── Correctness Filtering  ── keep trajectories with correct final answers
  │                              → 9,365 trajectories
  └── Turn-Aware Resampling  ── upweight longer trajectories to emphasize
                                 deep research behavior
                                 → 18,745 final SFT instances

For RL, we use open QA supervision curated from the REDSearcher RL data source.

✨ Demo

DR-Venus Demo Video

DeepResearch on problem:"《真探》第一季里有一句类似“useless spin”的台词出现在第几集？".

🚀 Quick Start

Each subdirectory has its own dependencies and entry scripts. Refer to the subproject READMEs for full details.

1. Inference

Run the trained model with search and visit tools:

cd Inference
pip install -r requirements.txt

# Configure API credentials used by the tool server first
bash run_demo.sh

# Or launch the web demo
bash run_web_demo.sh --model_path <MODEL_PATH> --num_gpus <NUM_GPUS>

See Inference/README.md for the full setup guide.

2. SFT

Prepare cleaned trajectories and train the SFT checkpoint:

cd SFT
pip install -e .
pip install -r requirements.txt

# Optional: convert raw RED trajectories into SFT-ready parquet
python data_clean/prepare_trajectories.py \
  --input <RAW_PARQUET_OR_DIR> \
  --output-dir <OUTPUT_DIR>

# Run supervised fine-tuning
bash train_sft.sh

See SFT/README.md for data format, environment variables, and checkpoint merging.

3. RL

Continue from the SFT checkpoint with long-horizon RL:

cd RL
pip install -r requirements.txt

# Edit .env and train_igpo.sh first
bash train_igpo.sh

See RL/README.md for reward configuration, rollout setup, and troubleshooting.

🔌 External Services

Both Inference/ and RL/ depend on external tools and model endpoints. SFT does not require these.

📁 Repository Layout

DR-Venus/
├── README.md
├── assets/
│   ├── dr-venus-overview.png
│   └── dr-venus-passk.png
├── SFT/
│   ├── data_clean/          # RED trajectory conversion & cleaning
│   ├── scripts/             # Checkpoint merge utilities
│   ├── sft_shells/
│   ├── train_sft.sh
│   └── README.md
├── RL/
│   ├── configs/
│   ├── data/
│   ├── tool_server/
│   ├── train_igpo.sh
│   └── README.md
├── Inference/
│   ├── tool_server/
│   ├── run_demo.sh
│   ├── run_web_demo.sh
│   └── README.md
└── model_cards/

🤝 Acknowledgements

DR-Venus builds on several strong open-source foundations:

• verl -- training infrastructure
• IGPO -- RL algorithmic foundation
• Tongyi DeepResearch -- deep research agent design references
• REDSearcher -- open-data trajectories and related tooling

📝 Citation

@article{venus2026drvenus,
  title={DR-Venus: Towards Frontier Edge-Scale Deep Research Agents with Only 10K Open Data},
  author={Venus Team and Dai, Sunhao and Deng, Yong and Lin, Jinzhen and Song, Yusheng and Wang, Guoqing and Wu, Xiaofeng and Zhou, Yuqi and Yang, Shuo and Ying, Zhenzhe and Zhang, Zhanwei and Meng, Changhua and Wang, Weiqiang},
  journal={arXiv preprint arXiv:2604.19859},
  year={2026}
}