# Dockerless：无需环境的编程智能体补丁验证器

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-06-26 08:00
- AIHOT 分数：42
- AIHOT 链接：https://aihot.virxact.com/items/cmr1ghdum02muslnly5gsluoq
- 原文链接：https://arxiv.org/abs/2606.28436

## AI 摘要

Dockerless是一种无需运行环境的智能体补丁验证器，通过仓库探索收集证据判断补丁正确性。在评估基准上，其AUC得分领先最强开源验证器14.3分。将Dockerless同时用作监督微调的轨迹筛选器和强化学习奖励信号，可实现完全无需环境的后训练流程。训练模型在SWE-bench Verified、Multilingual和Pro上解决率分别达62.0%、50.0%和35.2%，较Qwen3.5-9B基线高出2.4、8.7和2.9个百分点，性能与基于环境的后训练持平。

## 正文

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.