Copertina

Lingma SWE-GPT: An Open Development-Process-Centric Language Model for Automated Software Improvement

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Ma, Yingwei, Cao, Rongyu, Cao, Yongchang, Zhang, Yue, Chen, Jue, Liu, Yibo, Liu, Yuchen, Li, Binhua, Huang, Fei, Li, Yongbin
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Software Engineering Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Alibaba LingmaAgent: Improving Automated Issue Resolution via Comprehensive Repository Exploration
di: Ma, Yingwei, et al.
Pubblicazione: (2024)

Codev-Bench: How Do LLMs Understand Developer-Centric Code Completion?
di: Pan, Zhenyu, et al.
Pubblicazione: (2024)

Thinking Longer, Not Larger: Enhancing Software Engineering Agents via Scaling Test-Time Compute
di: Ma, Yingwei, et al.
Pubblicazione: (2025)

LLMs as Continuous Learners: Improving the Reproduction of Defective Code in Software Issues
di: Lin, Yalan, et al.
Pubblicazione: (2024)

To Diff or Not to Diff? Structure-Aware and Adaptive Output Formats for Efficient LLM-based Code Editing
di: Cheng, Wei, et al.
Pubblicazione: (2026)

Do Code LLMs Understand Design Patterns?
di: Pan, Zhenyu, et al.
Pubblicazione: (2025)

Large Language Model Unlearning for Source Code
di: Jiang, Xue, et al.
Pubblicazione: (2025)

SWE-Dev: Evaluating and Training Autonomous Feature-Driven Software Development
di: Du, Yaxin, et al.
Pubblicazione: (2025)

Empowering RepoQA-Agent based on Reinforcement Learning Driven by Monte-carlo Tree Search
di: Li, Guochang, et al.
Pubblicazione: (2025)

InspectCoder: Dynamic Analysis-Enabled Self Repair through interactive LLM-Debugger Collaboration
di: Wang, Yunkun, et al.
Pubblicazione: (2025)

Kimi-Dev: Agentless Training as Skill Prior for SWE-Agents
di: Yang, Zonghan, et al.
Pubblicazione: (2025)

CodeRL+: Improving Code Generation via Reinforcement with Execution Semantics Alignment
di: Jiang, Xue, et al.
Pubblicazione: (2025)

ExploraCoder: Advancing code generation for multiple unseen APIs via planning and chained exploration
di: Wang, Yunkun, et al.
Pubblicazione: (2024)

Saber: An Efficient Sampling with Adaptive Acceleration and Backtracking Enhanced Remasking for Diffusion Language Model
di: Dong, Yihong, et al.
Pubblicazione: (2025)

SWE-Exp: Experience-Driven Software Issue Resolution
di: Chen, Silin, et al.
Pubblicazione: (2025)

Unveiling the Role of ChatGPT in Software Development: Insights from Developer-ChatGPT Interactions on GitHub
di: Li, Ruiyin, et al.
Pubblicazione: (2025)

SWE-rebench: An Automated Pipeline for Task Collection and Decontaminated Evaluation of Software Engineering Agents
di: Badertdinov, Ibragim, et al.
Pubblicazione: (2025)

Automated Extraction and Analysis of Developer's Rationale in Open Source Software
di: Dhaouadi, Mouna, et al.
Pubblicazione: (2025)

A Roadmap for Software Testing in Open Collaborative Development Environments
di: Wang, Qing, et al.
Pubblicazione: (2024)

EvoCodeBench: An Evolving Code Generation Benchmark with Domain-Specific Evaluations
di: Li, Jia, et al.
Pubblicazione: (2024)

Process-Centric Analysis of Agentic Software Systems
di: Liu, Shuyang, et al.
Pubblicazione: (2025)

A Viable Paradigm of Software Automation: Iterative End-to-End Automated Software Development
di: Li, Jia, et al.
Pubblicazione: (2025)

SWE-TRACE: Optimizing Long-Horizon SWE Agents Through Rubric Process Reward Models and Heuristic Test-Time Scaling
di: Han, Hao, et al.
Pubblicazione: (2026)

SWE-Next: Scalable Real-World Software Engineering Tasks for Agents
di: Liang, Jiarong, et al.
Pubblicazione: (2026)

daVinci-Env: Open SWE Environment Synthesis at Scale
di: Fu, Dayuan, et al.
Pubblicazione: (2026)

Prompt-Enhanced Software Vulnerability Detection Using ChatGPT
di: Zhang, Chenyuan, et al.
Pubblicazione: (2023)

DroidBot-GPT: GPT-powered UI Automation for Android
di: Wen, Hao, et al.
Pubblicazione: (2023)

SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution
di: Wei, Yuxiang, et al.
Pubblicazione: (2025)

Multi-Docker-Eval: A `Shovel of the Gold Rush' Benchmark on Automatic Environment Building for Software Engineering
di: Fu, Kelin, et al.
Pubblicazione: (2025)

Training Software Engineering Agents and Verifiers with SWE-Gym
di: Pan, Jiayi, et al.
Pubblicazione: (2024)

From SWE-ZERO to SWE-HERO: Execution-free to Execution-based Fine-tuning for Software Engineering Agents
di: Ludwig, Nikolai, et al.
Pubblicazione: (2026)

Unlocking Reproducibility: Automating re-Build Process for Open-Source Software
di: Hassanshahi, Behnaz, et al.
Pubblicazione: (2025)

SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering
di: Yang, John, et al.
Pubblicazione: (2024)

SWE-Bench++: A Framework for the Scalable Generation of Software Engineering Benchmarks from Open-Source Repositories
di: Wang, Lilin, et al.
Pubblicazione: (2025)

SWE-Cycle: Benchmarking Code Agents across the Complete Issue Resolution Cycle
di: Guan, Hao, et al.
Pubblicazione: (2026)

SWE-Sharp-Bench: A Reproducible Benchmark for C# Software Engineering Tasks
di: Mhatre, Sanket, et al.
Pubblicazione: (2025)

GSO: Challenging Software Optimization Tasks for Evaluating SWE-Agents
di: Shetty, Manish, et al.
Pubblicazione: (2025)

What's in a Benchmark? The Case of SWE-Bench in Automated Program Repair
di: Martinez, Matias, et al.
Pubblicazione: (2026)

SWE-Universe: Scale Real-World Verifiable Environments to Millions
di: Chen, Mouxiang, et al.
Pubblicazione: (2026)

SWE-Hub: A Unified Production System for Scalable, Executable Software Engineering Tasks
di: Zeng, Yucheng, et al.
Pubblicazione: (2026)