Code Critic Model

code-critic-model's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Articles

yiqingx 

updated a dataset about 1 month ago

code-critic-model/data_4B_dpo_pairs_8k

Viewer • Updated Oct 4 • 1.41k • 31

yiqingx 

published a dataset about 1 month ago

code-critic-model/data_4B_dpo_pairs_8k

Viewer • Updated Oct 4 • 1.41k • 31

shubhamrgandhi 

updated 2 models 2 months ago

code-critic-model/Qwen3-4B-Critic-SFT-DPO

Text Generation • 4B • Updated Sep 10 • 23

code-critic-model/Qwen3-4B-Critic-SFT

Text Generation • 4B • Updated Sep 10 • 20

shubhamrgandhi 

submitted a paper to Daily Papers 2 months ago

DRACO: Fine-Grained Credit Assignment with Dynamic Rubrics for Long-Horizon Agent Training

Paper • 2609.04094 • Published Sep 3 • 22

shubhamrgandhi 

authored 6 papers 2 months ago

StaticFixer: From Static Analysis to Static Repair

Paper • 2307.12465 • Published Jul 24, 2023

An Empirical Study on Strong-Weak Model Collaboration for Repo-level Code Generation

Paper • 2505.20182 • Published May 26, 2025

ResearchCodeAgent: An LLM Multi-Agent System for Automated Codification of Research Methodologies

Paper • 2504.20117 • Published Apr 28, 2025 • 1

Hybrid-Gym: Training Coding Agents to Generalize Across Tasks

Paper • 2602.16819 • Published Feb 18

When Agents go Astray: Course-Correcting SWE Agents with PRMs

Paper • 2509.02360 • Published Oct 21, 2025

Steer, Don't Solve: Training Small Critic Models for Large Code Agents

Paper • 2606.21811 • Published Jun 20 • 1

shubhamrgandhi 

updated 5 models 2 months ago

code-critic-model/Qwen3-4B-Critic-SFT-Qwen-only

Text Generation • 4B • Updated Sep 3 • 17

code-critic-model/Qwen3-8B-Critic-SFT-Detailed-Prompt

Text Generation • 1B • Updated Sep 3 • 13

code-critic-model/Qwen3-8B-Critic-SFT-CWM-only

Text Generation • 1B • Updated Sep 3 • 14

code-critic-model/Qwen3-8B-Critic-SFT-Qwen-only

Text Generation • 8B • Updated Sep 3 • 17

code-critic-model/Qwen3-8B-Critic-SFT

Text Generation • 1B • Updated Sep 3 • 27

shubhamrgandhi 

updated a collection 2 months ago

Steer, Don't Solve: critic models and data

Collection

Critic models and SFT corpora from 'Steer, Don't Solve: Training Small Critic Models for Large Code Agents' (arXiv 2606.21811). • 12 items • Updated Sep 3