mlsanityData to 7 Oct 2026

SWE-Master: Unleashing the Potential of Software Engineering Agents via Post-Training

arXiv 2602.03411 ↗First posted 3 Feb 2026cs.SE cs.CLcited by 18

On the map: LLM agents and tool use → Software engineering coding agents

Abstract (arXiv)

In this technical report, we present SWE-Master, an open-source and fully reproducible post-training framework for building effective software engineering agents. SWE-Master systematically explores the complete agent development pipeline, including teacher-trajectory synthesis and data curation, long-horizon SFT, RL with real execution feedback, and inference framework design. Starting from an open-source base model with limited initial SWE capability, SWE-Master demonstrates how systematical optimization method can elicit strong long-horizon SWE task solving abilities. We evaluate SWE-Master on SWE-bench Verified, a standard benchmark for realistic software engineering tasks. Under identical experimental settings, our approach achieves a resolve rate of 61.4% with Qwen2.5-Coder-32B, substantially outperforming existing open-source baselines. By further incorporating test-time scaling~(TTS) with LLM-based environment feedback, SWE-Master reaches 70.8% at TTS@8, demonstrating a strong performance potential. SWE-Master provides a practical and transparent foundation for advancing reproducible research on software engineering agents. The code is available at https://github.com/RUCAIBox/SWE-Master.

Key facts. Cited by 18 papers in the map (data through 7 Oct 2026). Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use. Builds on 47 of its 66 references that are in the map. First posted on arXiv 3 Feb 2026.

Builds on

47 of 66 references.

Closest ancestors · 11

Same direction, newest first

  1. 2026daVinci-Dev: Agent-native Mid-training for Software Engineering26 Jan
  2. 2026SWE-Pruner: Self-Adaptive Context Pruning for Coding Agents23 Jan
  3. 2025Context as a Tool: Context Management for Long-Horizon SWE-Agents26 Dec
  4. 2025SWE-RM: Execution-free Feedback For Software Engineering Agents26 Dec
  5. 2025Confucius Code Agent: Scalable Agent Scaffolding for Real-World Codebases11 Dec
  6. 2025The OpenHands Software Agent SDK: A Composable and Extensible Foundation for Production Agents5 Nov
  7. 2025Kimi-Dev: Agentless Training as Skill Prior for SWE-Agents27 Sep
  8. 2025Skywork-SWE: Unveiling Data Scaling Laws for Software Engineering in LLMs24 Jun
  9. 2025R2E-Gym: Procedural Environments and Hybrid Verifiers for Scaling Open-Weights SWE Agents9 Apr
  10. 2024Training Software Engineering Agents and Verifiers with SWE-Gym30 Dec
  11. 2024SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering6 May

Other references · 36

  1. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  3. 2025Qwen3 Technical Reportcited by 8,195
  4. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  5. 2023SWE-bench: Can Language Models Resolve Real-World GitHub Issues?cited by 3,193
  6. 2025DAPO: An Open-Source LLM Reinforcement Learning System at Scalecited by 2,678
  7. 2024Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameterscited by 1,928
  8. 2024LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Codecited by 1,906
  9. 2024Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scalingcited by 1,573
  10. 2025Understanding R1-Zero-Like Training: A Critical Perspectivecited by 1,276
  11. 2025gpt-oss-120b & gpt-oss-20b Model Cardcited by 1,258
  12. 2024DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligencecited by 1,154
24 more
  1. 2024Qwen2.5-Coder Technical Reportcited by 1,151
  2. 2025DeepSeek-V3.2: Pushing the Frontier of Open Large Language Modelscited by 755
  3. 2025BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agentscited by 616
  4. 2026Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfacescited by 515
  5. 2025GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Modelscited by 446
  6. 2025R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learningcited by 322
  7. 2025SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?cited by 254
  8. 2024SWE-bench Multimodal: Do AI Systems Generalize to Visual Software Domains?cited by 196
  9. 2026MiMo-V2-Flash Technical Reportcited by 163
  10. 2025Scaling Long-Horizon LLM Agent via Context-Foldingcited by 136
  11. 2025Reinforcement Learning Optimization for Large-Scale Learning: An Efficient and User-Friendly Scaling Librarycited by 94
  12. 2025SWE-Fixer: Training Open-Source LLMs for Effective and Efficient GitHub Issue Resolutioncited by 87
  13. 2025CWM: An Open-Weights LLM for Research on Code Generation with World Modelscited by 87
  14. 2025SkyRL-Agent: Efficient RL Training for Multi-turn LLM Agentcited by 44
  15. 2025Budget-Aware Tool Use Enables Effective Agent Scalingcited by 42
  16. 2025Training Long-Context, Multi-Turn Software Engineering Agents with Reinforcement Learningcited by 34
  17. 2025SWE-Mirror: Scaling Issue-Resolving Datasets by Mirroring Issues Across Repositoriescited by 30
  18. 2026SWE-Lego: Pushing the Limits of Supervised Fine-tuning for Software Issue Resolvingcited by 30
  19. 2025BugPilot: Complex Bug Generation for Efficient Learning of SWE Skillscited by 28
  20. 2025ManuSearch: Democratizing Deep Search in Large Language Models with a Transparent and Open Multi-Agent Frameworkcited by 11
  21. 2026Computer Environments Elicit General Agentic Intelligence in LLMscited by 11
  22. 2025Scaling Code-Assisted Chain-of-Thoughts and Instructions for Model Reasoningcited by 10
  23. 2026Advances and Frontiers of LLM-based Issue Resolution in Software Engineering: A Comprehensive Surveycited by 8
  24. 2025InfCode-C++: Intent-Guided Semantic Retrieval and AST-Structured Search for C++ Issue Resolutioncited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 18.

18 papers.

Sort:

By area:

  1. 2026daVinci-Env: Open SWE Environment Synthesis at Scalecited by 13
  2. 2026SWE-TRACE: Optimizing Long-Horizon SWE Agents Through Rubric Process Reward Models and Heuristic Test-Time Scalingcited by 12
  3. 2026SWE-MeM: Learning Adaptive Memory Management for Long-Horizon Coding Agentscited by 12
  4. 2026ClawGym: A Scalable Framework for Building Effective Claw Agentscited by 11
  5. 2026Orchard: An Open-Source Agentic Modeling Frameworkcited by 7
  6. 2026From SWE-ZERO to SWE-HERO: Execution-free to Execution-based Fine-tuning for Software Engineering Agentscited by 5
  7. 2026Open-SWE-Traces: Advancing Dual-Mode Multilingual Distillation for Software Engineering Agentscited by 5
  8. 2026CalibForge: Adversarial Solver Calibration for Scaling Learnable Terminal Taskscited by 5
  9. 2026FastContext: Training Efficient Repository Explorer for Coding Agentscited by 4
  10. 2026SWE-Prime: Fewer Trajectories, Better Performancecited by 3
  11. 2026Yet Even Less Is Even Better For Agentic, Reasoning, and Coding LLMscited by 2
  12. 2026ClawGym II: Exploring Black-Box RL on Agent Harnesscited by 2
6 more
  1. 2026Terminal Agents: A Survey of AI Agents in Command-Line Environmentscited by 0
  2. 2026Feyospace-v1: How the Cyber Mercury Seven Trained Frontier Cyber Modelscited by 0
  3. 2026One to More, More to One: Category-Aware Iterative Expert Training for Software Engineering Agentscited by 0
  4. 2026Agent-Editing World Model: Rethinking World Modeling for LLM Agentscited by 0
  5. 2026QwenGyre: An Elastic Reinforcement Learning Framework for Training xLong-Horizon Agentscited by 0
  6. 2026Can Language Models Learn to Forecast Stock Pricescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026SWE-World: Building Software Engineering Agents in Docker-Free Environments
  2. 2026SWE-Skills-Bench: Do Agent Skills Actually Help in Real-World Software Engineering?
  3. 2025SWE-Dev: Building Software Engineering Agents with Training and Inference Scaling
  4. 2025Training Versatile Coding Agents in Synthetic Environments
  5. 2026SWE-rebench V2: Language-Agnostic SWE Task Collection at Scale
  6. 2025SWE-rebench: An Automated Pipeline for Task Collection and Decontaminated Evaluation of Software Engineering Agents
  7. 2026SWE-Next: Scalable Real-World Software Engineering Tasks for Agents
  8. 2026SWE-Replay: Efficient Test-Time Scaling for Software Engineering Agents