無Docker：面向編碼智能體的環境無關程式驗證器

摘要

程式驗證器在訓練編碼代理中扮演核心角色，包括為監督微調（SFT）篩選軌跡，以及為強化學習（RL）提供獎勵。標準的基於執行驗證需要在每個倉庫的環境（如 Docker 映像）中執行單元測試，這會導致相當高的環境建置成本。我們提出了 Dockerless，這是一種無需環境的代理式補丁驗證器，能在不執行程式碼的情況下評估生成的程式補丁。Dockerless 並非簡單地將候選補丁與參考補丁進行比對，而是透過代理式倉庫探索所收集的證據來判斷補丁的正確性。在驗證器評估基準上，Dockerless 比最強的開源驗證器高出 14.3 個 AUC 分數。將 Dockerless 同時用作 SFT 軌跡篩選器和 RL 獎勵，可以實現完全無環境的後訓練流程。由此產生的模型在 SWE-bench Verified、Multilingual 和 Pro 上分別達到了 62.0%、50.0% 和 35.2% 的解決率。它超越了 Qwen3.5-9B 基線模型 2.4、8.7 和 2.9 個百分點，性能可與基於環境的後訓練方法媲美。

English

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.