Dockerless: Environment-Free Program Verifier for Coding Agents
For coding agent training, Dockerless eliminates the need for per-repository environment setup, reducing costs while maintaining performance comparable to environment-based methods.
Dockerless is an environment-free program verifier that evaluates code patches without execution, using agentic repository exploration. It outperforms the strongest open-source verifier by 14.3 AUC points and enables a fully environment-free post-training pipeline, achieving resolve rates of 62.0%, 50.0%, and 35.2% on SWE-bench Verified, Multilingual, and Pro, respectively.
Program verifiers play a central role in training coding agents, including selecting trajectories for supervised fine-tuning (SFT) and providing rewards for reinforcement learning (RL). Standard execution-based verification requires running unit tests inside per-repository environments such as Docker images, incurring substantial environment setup costs. We propose Dockerless, an environment-free agentic patch verifier that evaluates generated code patches without executing them. Rather than simply matching candidate patches to references, Dockerless judges patch correctness using evidence gathered through agentic repository exploration. On a verifier evaluation benchmark, Dockerless outperforms the strongest open-source verifier by 14.3 AUC points. Using Dockerless as both the SFT trajectory filter and the RL reward enables a fully environment-free post-training pipeline. The resulting model reaches 62.0%, 50.0%, and 35.2% resolve rate on SWE-bench Verified, Multilingual, and Pro, respectively. It surpasses the Qwen3.5-9B baseline by 2.4, 8.7, and 2.9 points, matching environment-based post-training.