SWE-Universe: Scale Real-World Verifiable Environments to Millions

TL;DR

SWE-Universe introduces a scalable framework for automatically creating millions of real-world software engineering environments from GitHub pull requests, enabling large-scale training and evaluation of coding agents.

Contribution

It presents a novel, efficient method for generating high-fidelity, verifiable SWE environments at unprecedented scale using a custom-trained building agent.

Findings

Scaled to 807,693 environments, enabling extensive testing.

Achieved 75.3% score on SWE-Bench Verified with Qwen3-Max-Thinking.

Demonstrated effectiveness in large-scale agent training and reinforcement learning.

Abstract

We propose SWE-Universe, a scalable and efficient framework for automatically constructing real-world software engineering (SWE) verifiable environments from GitHub pull requests (PRs). To overcome the prevalent challenges of automatic building, such as low production yield, weak verifiers, and prohibitive cost, our framework utilizes a building agent powered by an efficient custom-trained model. This agent employs iterative self-verification and in-loop hacking detection to ensure the reliable generation of high-fidelity, verifiable tasks. Using this method, we scale the number of real-world multilingual SWE environments to a million scale (807,693). We demonstrate the profound value of our environments through large-scale agentic mid-training and reinforcement learning. Finally, we applied this technique to Qwen3-Max-Thinking and achieved a score of 75.3% on SWE-Bench Verified. Our work provides both a critical resource and a robust methodology to advance the next generation of coding agents.