Logics-SWE-Qwen3.6-35B-A3B is a software engineering model developed from Qwen3.6-35B-A3B using category-aware multi-teacher on-policy distillation (MOPD). It brings together the capabilities of three software engineering experts in a single model for repository-level coding agents.
One policy, three experts. The model integrates three category experts into one student that can work across repository domains without selecting an expert at inference time.
Reuse of 27B teachers. The same three final Qwen3.6-27B-based experts used for Logics-SWE-Qwen3.6-27B are reused to train the 35B-A3B student.
Improved SWE and coding results. Compared with Qwen3.6-35B-A3B, the model improves by 3.69 points on SWE-bench Pro V2, 3.00 points on SWE-bench Multilingual, and 2.37 points on SWE-bench Pro.
Repository-level software engineering tasks span different domains, from services and data systems to user-facing applications and developer tools. The RRE–MOPD approach develops complementary specialists and combines their knowledge into a single agent model:
Organize tasks. SWE Labeler assigns tasks to repository-domain categories: service, data and security; user-facing applications; and systems, tooling and runtimes.
Develop experts. Three Qwen3.6-27B-based experts are trained with Refresh–Repair–Expand (RRE), alternating agentic reinforcement learning, mastery refreshes, and supervised repair on verified successful trajectories.
Integrate with MOPD. A student initialized from Qwen3.6-35B-A3B generates its own trajectories and receives token-level guidance from the expert corresponding to each training task. The student's initial policy serves as the frozen reference for extrapolation.
The final model runs as a single policy. It does not require the three experts or category routing when deployed.
The model is intended for research and development on repository-level software engineering agents, including codebase exploration, issue diagnosis, code editing, test execution, and iterative debugging. A coding-agent harness can provide the model with repository access, tools, execution feedback, and a workspace in which to build and validate a patch.
For a local copy of the model, a vLLM server can be started with:
vllm serve /path/to/Logics-SWE-Qwen3.6-35B-A3B
The server exposes an OpenAI-compatible API for integration with a coding-agent harness. Use the model's tokenizer and chat template when constructing requests. See the Qwen model card and vLLM documentation for serving setup.
The public Logics-SWE-Env-2.5K release provides 2,553 software engineering task instances and matching environment-image references. The AgenticBigBang repository contains SWE Labeler, research artifacts, and evaluation materials.
@misc{zhao2026onetomoremoretoone,
title = {One to More, More to One: Category-Aware Iterative Expert Training for Software Engineering Agents},
author = {Jie Zhao and Ziyu Jiang and Suhang Zheng and Minghui Shan and Xiaoxiao Xu and Lin Qu},
year = {2026},
eprint = {2609.23377},
archivePrefix = {arXiv},
primaryClass = {cs.SE},
url = {https://arxiv.org/abs/2609.23377}
}
We thank the Qwen, ROLL, R2E-Gym, SWE-agent, SWE-bench, SWE-bench Pro, and SWE-bench Multilingual contributors, and the research communities behind MiniRL, MOPD, and ExOPD.
import os
os.environ["HF_ENDPOINT"] = "https://freeweights.allternit.com"
from transformers import AutoModelForCausalLM, AutoTokenizer
tok = AutoTokenizer.from_pretrained("Logics-MLLM/Logics-SWE-Qwen3.6-35B-A3B", revision="8a8ae508b9143423fa4cbf88982d69f01e11111e")
model = AutoModelForCausalLM.from_pretrained("Logics-MLLM/Logics-SWE-Qwen3.6-35B-A3B", revision="8a8ae508b9143423fa4cbf88982d69f01e11111e", device_map="auto")
BAAI