SWE-Critix: Post-Training Generalist Verifiers for Assessing Coding-Agent Trajectories
We introduce SWE-Critix, a post-training pipeline for training generalist verifiers of coding-agent trajectories.
ProofPaper ↗
Key points
- Coding agents are increasingly deployed for end-to-end software engineering tasks, where a readily available oracle evaluator that defines the success criteria is often absent.
- This motivates verifications for coding agents that can reliably judge and explain their behavior.
- However, verification is non-trivial as coding agents are increasingly capable of solving long-horizon software engineering tasks.
- Our pipeline combines supervised fine-tuning (SFT) with reinforcement learning (RL) and trains a series of 30B models on trajectories from CodeForge-Preview.
Sources (1)
- [1]SWE-Critix: Post-Training Generalist Verifiers for Assessing Coding-Agent TrajectoriesarXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 9, 10:30 AM
We introduce SWE-Critix, a post-training pipeline for training generalist verifiers of coding-agent trajectories.
Coding agents are increasingly deployed for end-to-end software engineering tasks, where a readily available oracle evaluator that defines the success criteria is often absent.
Extractive summary: sentences quoted from the sources.
Before this
- Oct 9, 2026VIGOR: Verifiable Industrial Geometry Optimization and Repair in Scene Programs
- Oct 9, 2026Qwen/Qwen-Image-2.1-Turbo
- Oct 9, 2026Robust Langevin Sampling under State-Dependent Heavy-Tailed Noise with Applications to LLM Fine-Tuning
- Oct 9, 2026Cross-Behavior Policy Optimization: Unified Learning from Offline Demonstrations and On- and Off-Policy Rollouts via a Shared Regression Target
- Oct 8, 2026Unsupervised Multimodal Reward Modeling
- Oct 8, 2026Understanding Jev, the new model everyone is talking about
