GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
XLearning-SCU
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
XLearning-SCU
Model Tree
Qwen/Qwen3.5-4B
Input Modalities
Output Modalities
Supported Functionality
HERO-4B is post-trained from Qwen3.5-4B using HERO (HiErarchical ReinfOrcement learning) to improve token efficiency while prioritizing task resolution.
| Item | Description |
|---|---|
| Base model | Qwen/Qwen3.5-4B |
| Parameters | 4B (dense) |
| Architecture and tokenizer | Inherited from Qwen3.5-4B |
| Training | HERO on 640 multilingual SWE tasks from SWE-Gym, Multi-SWE-bench, and SWE-rebench |
| Intended use | Repository-level coding agents |
| Format | Hugging Face weights and tokenizer |
HERO combines capability-based efficiency gating, resolution-first clipping, and efficiency credit at trajectory and turn levels. Qwen3.5 is the backbone; this release contains the HERO post-trained weights.
Follow the preparation guide in the HERO code repository. From that repository's root,
with this model saved under ../models/HERO-4B/:
bash
MODEL=../models/HERO-4B bash eval/run_eval_swebench_verified.shMODEL=../models/HERO-4B bash eval/run_eval_swebench_multilingual.shThe released evaluation scripts use the following defaults for both SWE-bench Verified and SWE-bench Multilingual:
| Setting | Value |
|---|---|
| Agent scaffold | Claude Code |
| Inference backend | SGLang |
| Temperature | 0.6 |
| Top-p | 0.95 |
| Context length | 131,072 tokens |
| Maximum output per call | 16,000 tokens |
| Maximum agent turns | 200 |
| Automatic context compaction | Disabled |
| Tools | Default tools, excluding WebFetch, WebSearch, and Agent |
See the evaluation script for configuration options.
Apache-2.0. See LICENSE. We acknowledge the Qwen team for the base model.
If you find HERO useful, please cite our paper:
bibtex
@misc{li2026hero, title = {Doing More with Less Tokens: Hierarchical Reinforcement Learning for Efficient Coding Agents}, author = {Haobin Li and Liang Jiang and Zhenyu Huang and Mouxing Yang and Xi Peng}, year = {2026}, eprint = {2609.38885}, archivePrefix = {arXiv}, primaryClass = {cs.SE}, url = {https://arxiv.org/abs/2609.38885}}MODEL=../models/HERO-4B bash eval/run_eval_swebench_verified.shMODEL=../models/HERO-4B bash eval/run_eval_swebench_multilingual.sh@misc{li2026hero, title = {Doing More with Less Tokens: Hierarchical Reinforcement Learning for Efficient Coding Agents}, author = {Haobin Li and Liang Jiang and Zhenyu Huang and Mouxing Yang and Xi Peng}, year = {2026}, eprint = {2609.38885}, archivePrefix = {arXiv}, primaryClass = {cs.SE}, url = {https://arxiv.org/abs/2609.38885}}