code-critic-model/Qwen3-4B-Critic-SFT-Qwen-only
Text Generation • 4B • Updated • 414
messages listlengths 13 147 |
|---|
[
{
"role": "system",
"content": "You are a supervisor monitoring an LLM-based coding agent. Your role is to detect trajectory-level errors and provide corrective guidance to prevent task failure.\nAnalyze the provided agent trace for the following error categories. For each detected error, provide specific e... |
[
{
"role": "system",
"content": "You are a supervisor monitoring an LLM-based coding agent. Your role is to detect trajectory-level errors and provide corrective guidance to prevent task failure.\nAnalyze the provided agent trace for the following error categories. For each detected error, provide specific e... |
[
{
"role": "system",
"content": "You are a supervisor monitoring an LLM-based coding agent. Your role is to detect trajectory-level errors and provide corrective guidance to prevent task failure.\nAnalyze the provided agent trace for the following error categories. For each detected error, provide specific e... |
[
{
"role": "system",
"content": "You are a supervisor monitoring an LLM-based coding agent. Your role is to detect trajectory-level errors and provide corrective guidance to prevent task failure.\nAnalyze the provided agent trace for the following error categories. For each detected error, provide specific e... |
[
{
"role": "system",
"content": "You are a supervisor monitoring an LLM-based coding agent. Your role is to detect trajectory-level errors and provide corrective guidance to prevent task failure.\nAnalyze the provided agent trace for the following error categories. For each detected error, provide specific e... |
[
{
"role": "system",
"content": "You are a supervisor monitoring an LLM-based coding agent. Your role is to detect trajectory-level errors and provide corrective guidance to prevent task failure.\nAnalyze the provided agent trace for the following error categories. For each detected error, provide specific e... |
[
{
"role": "system",
"content": "You are a supervisor monitoring an LLM-based coding agent. Your role is to detect trajectory-level errors and provide corrective guidance to prevent task failure.\nAnalyze the provided agent trace for the following error categories. For each detected error, provide specific e... |
[{"role":"system","content":"You are a supervisor monitoring an LLM-based coding agent. Your role is(...TRUNCATED) |
[{"role":"system","content":"You are a supervisor monitoring an LLM-based coding agent. Your role is(...TRUNCATED) |
[{"role":"system","content":"You are a supervisor monitoring an LLM-based coding agent. Your role is(...TRUNCATED) |
End of preview. Expand in Data Studio
critic-sft-qwen-only
The Qwen-only SFT corpus from Steer, Don't Solve: Training Small Critic Models for Large Code Agents. It trains Qwen3-8B-Critic-SFT-Qwen-only and Qwen3-4B-Critic-SFT-Qwen-only, the Qwen-only arms of the corpus ablation in Table 3.
Each record is one critique point: a Qwen3-Next-80B-A3B-Instruct trajectory up to some step, followed by the critique that Claude Opus 4.6 wrote for it under the paper's high-level prompt. The main corpus, critic-sft-cwm-qwen, is this set plus 4,532 records from CWM-32B trajectories.
| Records | 1,915 |
| Trajectories | 483, all from Qwen3-Next-80B-A3B-Instruct |
| Tasks | 483 R2E-Gym instances from matplotlib, moto, and sympy, disjoint from SWE-bench Verified |
| Teacher | Claude Opus 4.6 (us.anthropic.claude-opus-4-6-v1), queried every 5 agent steps |
| Teacher prompt | high-level (prm_issue_res_instructions in the repository) |
| Agent scaffold | mini-swe-agent, one bash command per step |
| Length limit | 32,768 tokens per record |
The set is smaller than the CWM one because Qwen3-Next finishes tasks in fewer steps, so fewer critique points are collected per trajectory. The tasks are the same 500 used for CWM, minus 17 on which the Qwen3-Next run produced no usable trajectory.
Format
One JSON object per line with a single field, messages, in ShareGPT layout: a system turn with the critic instructions, alternating user / assistant turns carrying the agent's trajectory (task and command output on the user side, agent reasoning and bash command on the assistant side), and a final assistant turn holding the teacher critique. Critiques the agent received earlier in the trajectory appear inside the user turn that follows them. The full description of the format, with an example critique, is on the critic-sft-cwm-qwen card.
Files
| File | Purpose |
|---|---|
prm_sft_train.jsonl |
the records |
dataset_info.json |
LLaMA-Factory dataset registration (sharegpt format) |
metadata.json |
provenance: source run, agent, teacher, counts, instance ids |
Using it
from datasets import load_dataset
ds = load_dataset("code-critic-model/critic-sft-qwen-only", split="train")
For LLaMA-Factory, point dataset_dir at a download of this repository and use dataset: prm_sft_train with the configs in finetuning/ of the critic-training repository.
Citation
@misc{gandhi2026steerdontsolvetraining,
title={Steer, Don't Solve: Training Small Critic Models for Large Code Agents},
author={Shubham Gandhi and Yiqing Xie and Atharva Naik and Ruichen Zhu and Carolyn Rose},
year={2026},
eprint={2606.21811},
archivePrefix={arXiv},
primaryClass={cs.SE},
url={https://arxiv.org/abs/2606.21811}
}
- Downloads last month
- 29