SERA: Soft-Verified Efficient Repository Agents

TL;DR

SERA introduces a cost-effective, supervised fine-tuning method for creating specialized open-source coding agents capable of private codebase adaptation, matching state-of-the-art performance with significantly reduced training costs.

Contribution

The paper presents SERA, a novel training approach that enables rapid, cheap, and effective specialization of open-source coding agents to private codebases using supervised fine-tuning.

Findings

SERA achieves state-of-the-art results among open-source models.

Creating SERA is 26x cheaper than reinforcement learning.

Generating synthetic trajectories enables large-scale codebase training.

Abstract

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.