SFT-trained step-level critic (Qwen3-8B) for code agents on SWE-bench Verified. Companion to https://github.com/shubhamrgandhi/critic-training
Shubham Gandhi
shubhamrgandhi
·
AI & ML interests
AI4Code
Recent Activity
updated a model about 2 months ago
code-critic-model/Qwen3-4B-Critic-SFT-DPO updated a model about 2 months ago
code-critic-model/Qwen3-4B-Critic-SFT commentedon a paper 2 months ago
DRACO: Fine-Grained Credit Assignment with Dynamic Rubrics for Long-Horizon Agent TrainingOrganizations
