Imagen de Portada

Otter: Generating Tests from Issues to Validate SWE Patches

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Ahmed, Toufique, Ganhotra, Jatin, Pan, Rangeet, Shinnar, Avraham, Sinha, Saurabh, Hirzel, Martin
Formato:	Preprint
Publicado:	2025
Materias:	Software Engineering Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Investigating Test Overfitting on SWE-bench
por: Ahmed, Toufique, et al.
Publicado: (2025)

Reproduction Test Generation for Java SWE Issues
por: Ahmed, Toufique, et al.
Publicado: (2026)

Heterogeneous Prompting and Execution Feedback for SWE Issue Test Generation and Selection
por: Ahmed, Toufique, et al.
Publicado: (2025)

TDD-Bench Verified: Can LLMs Generate Tests for Issues Before They Get Resolved?
por: Ahmed, Toufique, et al.
Publicado: (2024)

Resolving Java Code Repository Issues with iSWE Agent
por: Ganhotra, Jatin, et al.
Publicado: (2026)

Can Old Tests Do New Tricks for Resolving SWE Issues?
por: Chen, Yang, et al.
Publicado: (2025)

AlphaTrans: A Neuro-Symbolic Compositional Approach for Repository-Level Code Translation and Validation
por: Ibrahimzada, Ali Reza, et al.
Publicado: (2024)

Sakura: An Approach for Generating Complex Tests from Natural Language Test Descriptions
por: Stennett, Tyler, et al.
Publicado: (2026)

ASTER: Natural and Multi-language Unit Test Generation with LLMs
por: Pan, Rangeet, et al.
Publicado: (2024)

Evaluating Plan Compliance in Autonomous Programming Agents
por: Liu, Shuyang, et al.
Publicado: (2026)

When Agents go Astray: Course-Correcting SWE Agents with PRMs
por: Gandhi, Shubham, et al.
Publicado: (2025)

CoDocBench: A Dataset for Code-Documentation Alignment in Software Maintenance
por: Pai, Kunal, et al.
Publicado: (2025)

Studying LLM Performance on Closed- and Open-source Data
por: Ahmed, Toufique, et al.
Publicado: (2024)

Hamster: A Large-Scale Study and Characterization of Developer-Written Tests
por: Pan, Rangeet, et al.
Publicado: (2025)

Automatic Semantic Augmentation of Language Model Prompts (for Code Summarization)
por: Ahmed, Toufique, et al.
Publicado: (2023)

Advancing Automated In-Isolation Validation in Repository-Level Code Translation
por: Ke, Kaiyao, et al.
Publicado: (2025)

SWE Atlas: Benchmarking Coding Agents Beyond Issue Resolution
por: Raghavendra, Mohit, et al.
Publicado: (2026)

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

SWE-Tester: Training Open-Source LLMs for Issue Reproduction in Real-World Repositories
por: Soni, Aditya Bharat, et al.
Publicado: (2026)

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

SWE-Replay: Efficient Test-Time Scaling for Software Engineering Agents
por: Ding, Yifeng, et al.
Publicado: (2026)

Can LLMs Replace Manual Annotation of Software Engineering Artifacts?
por: Ahmed, Toufique, et al.
Publicado: (2024)

Trojans in Large Language Models of Code: A Critical Review through a Trigger-Based Taxonomy
por: Hussain, Aftab, et al.
Publicado: (2024)

How Safe Are AI-Generated Patches? A Large-scale Study on Security Risks in LLM and Agentic Automated Program Repair on SWE-bench
por: Sajadi, Amirali, et al.
Publicado: (2025)

Codellm-Devkit: A Framework for Contextualizing Code LLMs with Program Analysis Insights
por: Krishna, Rahul, et al.
Publicado: (2024)

Prompting and Fine-tuning Large Language Models for Automated Code Review Comment Generation
por: Haider, Md. Asif, et al.
Publicado: (2024)

SWE-Debate: Competitive Multi-Agent Debate for Software Issue Resolution
por: Li, Han, et al.
Publicado: (2025)

SWE-Arena: An Interactive Platform for Evaluating Foundation Models in Software Engineering
por: Zhao, Zhimin
Publicado: (2025)

SAINT: Service-level Integration Test Generation with Program Analysis and LLM-based Agents
por: Pan, Rangeet, et al.
Publicado: (2025)

Towards Understanding What Code Language Models Learned
por: Ahmed, Toufique, et al.
Publicado: (2023)

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

SWE-Lancer: Can Frontier LLMs Earn $1 Million from Real-World Freelance Software Engineering?
por: Miserendino, Samuel, et al.
Publicado: (2025)

ITER: Iterative Neural Repair for Multi-Location Patches
por: Ye, He, et al.
Publicado: (2023)

SWE-Adept: An LLM-Based Agentic Framework for Deep Codebase Analysis and Structured Issue Resolution
por: He, Kang, et al.
Publicado: (2026)

Calibration and Correctness of Language Models for Code
por: Spiess, Claudio, et al.
Publicado: (2024)

SWE-Bench-CL: Continual Learning for Coding Agents
por: Joshi, Thomas, et al.
Publicado: (2025)

Timing Analysis Agent: Autonomous Multi-Corner Multi-Mode (MCMM) Timing Debugging with Timing Debug Relation Graph
por: Nainani, Jatin, et al.
Publicado: (2025)

Latent Regularization in Generative Test Input Generation
por: Merabishvili, Giorgi, et al.
Publicado: (2026)

SWE-MiniSandbox: Container-Free Reinforcement Learning for Building Software Engineering Agents
por: Yuan, Danlong, et al.
Publicado: (2026)

Beyond Verifiable Rewards: Rubric-Based GRM for Reinforced Fine-Tuning SWE Agents
por: Huang, Jiawei, et al.
Publicado: (2026)