GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
DAGroup-PKU
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
DAGroup-PKU
Model Tree
Qwen/Qwen3.5-4B
Input Modalities
Output Modalities
Supported Functionality
Success rate (%) in the PyRUA-Lean framework, one episode per task instance:
| Planner | Trained on (45) | LIBERO-PRO other tasks (155) | RoboTwin 2.0 (250) | RoboCasa365 atomic (90) | RoboCasa365 composite (160) | All unseen (655) | All (700) |
|---|---|---|---|---|---|---|---|
| Qwen3.5-4B | 37.8 | 13.5 | 14.0 | 52.2 | 12.5 | 18.8 | 20.0 |
| Qwen3.5-27B | 64.4 | 38.1 | 20.8 | 65.6 | 13.1 | 29.2 | 31.4 |
| PyRUA-Lean Coder v0.1-4B | 71.1 | 37.4 | 52.4 | 76.7 | 19.4 | 44.1 | 45.9 |
RoboTwin 2.0 and both RoboCasa365 sets are benchmarks the model was not trained on at all.
The model is served by any OpenAI-compatible server and driven by PyRUA-Lean's openai runtime. With SGLang:
bash
python -m sglang.launch_server --model-path DAGroup-PKU/PyRUA-Lean-Coder-v0.1-4B --port 30000 \ --context-length 65536 --tool-call-parser qwen3_coder --reasoning-parser qwen3 \ --constrained-json-disable-any-whitespaceThen one LIBERO-PRO episode, on a task the model never saw in training (RPent's LIBERO-PRO stack installed as the Quick Start describes):
bash
export RPENT_ROOT=/path/to/rpent OPENAI_API_KEY=nonepyrualean play --robot libero --arm cells --suite libero_goal_swap --task 3 --seed 0 \ --runtime openai --base-url http://127.0.0.1:30000/v1 --api-key-env OPENAI_API_KEY \ --model DAGroup-PKU/PyRUA-Lean-Coder-v0.1-4B \ --openai-max-tokens 8192 --openai-tool-choice required --openai-temperature 1.0 \ --openai-extra-body '{"top_p": 0.95, "top_k": 20}' \ --images on-demand --feedback pure --guides --max-turns 40 --budget-s 5400 \ --out runs/coder-demo --cuda-device 0pyrualean summarize runs/coder-demoThese are the settings of the paper's evaluation. The model is trained for the PyRUA-Lean prompt and tools; outside them it behaves like a general 4B chat model.
GRPO from Qwen3.5-4B in the PyRUA-Lean framework, on 45 LIBERO-PRO task instances; Section 5 of the paper describes it.
bibtex
@article{si2026fewer, title={Fewer tokens, better action: GPT-6 Astra robot agents with 14\% higher success rate but 65\% fewer tokens}, author={Si, Ruiyang and Bi, Jianxin and Yang, Shunyu and Ni, Rui and Huang, Wenbo and Wang, Qiang and Jiang, Shulong and Zhang, Yintianrun and Ruan, Feixiang and Zhang, Kewei and Wang, Duomin and Li, Xiuyu and Feng, Haiwen and Dong, Zhen and Zhou, Daquan}, journal={arXiv preprint arXiv:2610.01939}, year={2026}}The model inherits the Apache 2.0 license of Qwen3.5-4B.
python -m sglang.launch_server --model-path DAGroup-PKU/PyRUA-Lean-Coder-v0.1-4B --port 30000 \ --context-length 65536 --tool-call-parser qwen3_coder --reasoning-parser qwen3 \ --constrained-json-disable-any-whitespaceexport RPENT_ROOT=/path/to/rpent OPENAI_API_KEY=nonepyrualean play --robot libero --arm cells --suite libero_goal_swap --task 3 --seed 0 \ --runtime openai --base-url http://127.0.0.1:30000/v1 --api-key-env OPENAI_API_KEY \ --model DAGroup-PKU/PyRUA-Lean-Coder-v0.1-4B \ --openai-max-tokens 8192 --openai-tool-choice required --openai-temperature 1.0 \ --openai-extra-body '{"top_p": 0.95, "top_k": 20}' \ --images on-demand --feedback pure --guides --max-turns 40 --budget-s 5400 \ --out runs/coder-demo --cuda-device 0pyrualean summarize runs/coder-demo@article{si2026fewer, title={Fewer tokens, better action: GPT-6 Astra robot agents with 14\% higher success rate but 65\% fewer tokens}, author={Si, Ruiyang and Bi, Jianxin and Yang, Shunyu and Ni, Rui and Huang, Wenbo and Wang, Qiang and Jiang, Shulong and Zhang, Yintianrun and Ruan, Feixiang and Zhang, Kewei and Wang, Duomin and Li, Xiuyu and Feng, Haiwen and Dong, Zhen and Zhou, Daquan}, journal={arXiv preprint arXiv:2610.01939}, year={2026}}