Open-weight coding agents should hold a fundamental advantage over closed-source systems: they can be specialized to private codebases, encoding repository-specific information directly in their weights. Yet the cost and complexity of training has kept this advantage theoretical. We show it is now practical. We present Soft-Verified Efficient Repository Agents (SERA), an efficient method for training coding agents that enables the rapid and cheap creation of agents specialized to private codebases. Using only supervised finetuning (SFT), SERA achieves state-of-the-art results among fully open-source (open data, method, code) models while matching the performance of frontier open-weight models like Devstral-Small-2. Creating SERA models is 26x cheaper than reinforcement learning and 57x cheaper than previous synthetic data methods to reach equivalent performance. Our method, Soft Verified Generation (SVG), generates thousands of trajectories from a single code repository. Combined with cost-efficiency, this enables specialization to private codebases. Beyond repository specialization, we apply SVG to a larger corpus of codebases, generating over 200,000 synthetic trajectories. We use this dataset to provide detailed analysis of scaling laws, ablations, and confounding factors for training coding agents. Overall, we believe our work will greatly accelerate research on open coding agents and showcase the advantage of open-source models that can specialize to private codebases. We release SERA as the first model in Ai2's Open Coding Agents series, along with all our code, data, and Claude Code integration to support the research community.

翻译：开源权重编码智能体相对于闭源系统应具备一项根本优势：它们可以针对私有代码库进行专门化训练，将特定仓库信息直接编码到权重中。然而训练成本与复杂性使得这一优势长期停留在理论层面。我们证明其实用化现已可行。本文提出软验证高效代码库智能体（SERA），一种高效的编码智能体训练方法，能够快速低成本地创建针对私有代码库的专用智能体。仅通过监督微调（SFT），SERA在完全开源（开放数据、方法、代码）模型中取得了最先进的成果，同时达到了前沿开源权重模型（如Devstral-Small-2）的性能水平。创建SERA模型的成本比强化学习方法降低26倍，比先前合成数据方法降低57倍即可达到同等性能。我们的软验证生成（SVG）方法能够从单个代码库生成数千条训练轨迹。结合成本效益优势，该方法实现了对私有代码库的专门化适配。除仓库专门化外，我们将SVG应用于更大规模的代码库集合，生成了超过20万条合成轨迹。利用该数据集，我们对编码智能体训练的缩放规律、消融实验及混杂因素进行了详细分析。总体而言，我们相信这项工作将极大加速开源编码智能体的研究进程，并彰显可适配私有代码库的开源模型优势。我们将SERA作为Ai2开源编码智能体系列的首个模型发布，同时开放全部代码、数据及Claude Code集成方案，以支持研究社区的发展。