# SWE-Mirror: Scaling Issue-Resolving Datasets by Mirroring Issues Across Repositories

arXiv: https://arxiv.org/abs/2509.08724 · HTML: https://mlsanity.com/paper/2509.08724/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Sep 2025.

## Built on by (most cited first, 30 of 31)

- [Context as a Tool: Context Management for Long-Horizon SWE-Agents](https://mlsanity.com/paper/2512.22087/) (2025)
- [Large-Scale Terminal Agentic Trajectory Generation from Dockerized Environments](https://mlsanity.com/paper/2602.01244/) (2026)
- [SWE-Lego: Pushing the Limits of Supervised Fine-tuning for Software Issue Resolving](https://mlsanity.com/paper/2601.01426/) (2026)
- [BugPilot: Complex Bug Generation for Efficient Learning of SWE Skills](https://mlsanity.com/paper/2510.19898/) (2025)
- [SWE-World: Building Software Engineering Agents in Docker-Free Environments](https://mlsanity.com/paper/2602.03419/) (2026)
- [SWE-Master: Unleashing the Potential of Software Engineering Agents via Post-Training](https://mlsanity.com/paper/2602.03411/) (2026)
- [Immersion in the GitHub Universe: Scaling Coding Agents to Mastery](https://mlsanity.com/paper/2602.09892/) (2026)
- [BeyondSWE: Can Current Code Agent Survive Beyond Single-Repo Bug Fixing?](https://mlsanity.com/paper/2603.03194/) (2026)
- [daVinci-Dev: Agent-native Mid-training for Software Engineering](https://mlsanity.com/paper/2601.18418/) (2026)
- [SWE-MeM: Learning Adaptive Memory Management for Long-Horizon Coding Agents](https://mlsanity.com/paper/2606.28434/) (2026)
- [daVinci-Env: Open SWE Environment Synthesis at Scale](https://mlsanity.com/paper/2603.13023/) (2026)
- [Training Versatile Coding Agents in Synthetic Environments](https://mlsanity.com/paper/2512.12216/) (2025)
- [SERA: Soft-Verified Efficient Repository Agents](https://mlsanity.com/paper/2601.20789/) (2026)
- [Klear-AgentForge: Forging Agentic Intelligence through Posttraining Scaling](https://mlsanity.com/paper/2511.05951/) (2025)
- [What Makes Interaction Trajectories Effective for Training Terminal Agents?](https://mlsanity.com/paper/2606.03461/) (2026)
- [EvoConfig: Self-Evolving Multi-Agent Systems for Efficient Autonomous Environment Configuration](https://mlsanity.com/paper/2601.16489/) (2026)
- [Orchard: An Open-Source Agentic Modeling Framework](https://mlsanity.com/paper/2605.15040/) (2026)
- [Agentic Software Issue Resolution with Large Language Models: A Survey](https://mlsanity.com/paper/2512.22256/) (2025)
- [Gated Differentiable Working Memory for Long-Context Language Modeling](https://mlsanity.com/paper/2601.12906/) (2026)
- [SWE-MiniSandbox: Container-Free Reinforcement Learning for Building Software Engineering Agents](https://mlsanity.com/paper/2602.11210/) (2026)
- [MEnvAgent: Scalable Polyglot Environment Construction for Verifiable Software Engineering](https://mlsanity.com/paper/2601.22859/) (2026)
- [SWE-Hub: A Unified Production System for Scalable, Executable Software Engineering Tasks](https://mlsanity.com/paper/2603.00575/) (2026)
- [FrogNano: Training a 4B Coding Agent via Online Task Synthesis](https://mlsanity.com/paper/2609.07925/) (2026)
- [From Historical Patches to Repair Plans: Outcome-Conditioned Reasoning for Repository-Level Program Repair](https://mlsanity.com/paper/2601.23257/) (2026)
- [TREAT: A Code LLMs Trustworthiness / Reliability Evaluation and Testing Framework](https://mlsanity.com/paper/2510.17163/) (2025)
- [SWE-Fuse: Empowering Software Agents via Issue-free Trajectory Learning and Entropy-aware RLVR Training](https://mlsanity.com/paper/2603.07927/) (2026)
- [M2A: Synergizing Mathematical and Agentic Reasoning in Large Language Models](https://mlsanity.com/paper/2605.09879/) (2026)
- [SWE-Gate: Passing Functional Tests Is Not Enough for Software Engineering Agents](https://mlsanity.com/paper/2609.04167/) (2026)
- [SecProbe: Adaptive Evaluation of Coding Agents on Cybersecurity Vulnerabilities](https://mlsanity.com/paper/2609.33763/) (2026)
- [One Tool Is Enough: Reinforcement Learning for Repository-Level LLM Agents](https://mlsanity.com/paper/2512.20957/) (2025)

## Abstract (arXiv)

Creating large-scale verifiable training datasets for issue-resolving tasks is a critical yet notoriously difficult challenge. Existing methods on automating the Gym environment setup process for real-world issues suffer from low success rates and high overhead. Meanwhile, synthesizing new tasks within existing Gym environments leaves the vast pool of authentic, human-reported problems untapped. To maximize the utilization of existing Gym environments and also the rich data of issue-resolving history on GitHub, we introduce SWE-Mirror, a pipeline that distills a real-world issue's semantic essence, mirrors it into another repository with a configured Gym environment, and re-animates it as a verifiable issue-resolving task. SWE-Mirror reuses existing Gym environments along with the vast pool of issue-resolving history hosted on GitHub to construct a large-scale dataset of mirrored authentic and verifiable tasks. Applying SWE-Mirror to 40 repositories across 4 languages, we have curated a dataset with 60,671 issue-resolving tasks and demonstrated the value of our dataset by training and evaluating coding agents at various scale. Post-training experiments show that models trained with the dataset exhibit improvements in issue-resolving capabilities. Furthermore, by extending the dataset size to over 12,000 high-quality trajectories, we established a new state-of-the-art (SOTA) among Qwen2.5-Coder-Instruct based LLMs on the OpenHands agent framework, which increases the resolve rate on SWE-Bench-Verified by +21.8% for the 7B model and +46.0% for the 32B model and validates the effectiveness of our approach.