A 4B critic from
Steer, Don't Solve: Training Small Critic Models for Large Code Agents, trained on critiques of Qwen3-Next-80B-A3B trajectories only. It is one arm of the training-corpus ablation (Table 3). The 4B critic trained on the mixed CWM plus Qwen3-Next corpus is
Qwen3-4B-Critic-SFT.
The critic reads a coding agent's trajectory every k steps and returns a structured critique: detected error categories, evidence, a recovery action, task status, and one line of overall guidance. It does not write the patch.
All released models and datasets are listed on the
organization page. Code and configs are in the
critic-training repository.
Identical to Qwen3-4B-Critic-SFT apart from the data. Full-parameter SFT with LLaMA-Factory, config finetuning/qwen3_4b_critic_full_sft_l40s_train_multiturn_resumable.yaml.
Resolve rate on SWE-bench Verified, from Table 3 of the paper.
Same serving and launch procedure as
Qwen3-4B-Critic-SFT: serve with vLLM in bf16 and pass the served name to
scripts/run_critic_max150.sh with
--prm. The served name must have an entry in
mini-swe-agent/configs/litellm_model_registry.json; add one for this model if you use a new name.
1@misc{gandhi2026steerdontsolvetraining,
2 title={Steer, Don't Solve: Training Small Critic Models for Large Code Agents},
3 author={Shubham Gandhi and Yiqing Xie and Atharva Naik and Ruichen Zhu and Carolyn Rose},
4 year={2026},
5 eprint={2606.21811},
6 archivePrefix={arXiv},
7 primaryClass={cs.SE},
8 url={https://arxiv.org/abs/2606.21811}
9}
