4 papers
To Add Is Machine, To Delete Is Human: Measuring and Mitigating Deletion Avoidance in LLM Code Editing
Amir M. Ebrahimi, Mohammed Mehedi Hasan, Aaditya Bhatia +2
Large language models increasingly write and repair production code, yet evidence is mounting that their test-passing patches leave codebases harder to maintain. We identify one co…
An Empirical Study of Self-Admitted Technical Debt in Machine Learning Software
Aaditya Bhatia, Foutse Khomh, Bram Adams +1
The emergence of open-source ML libraries such as TensorFlow and Google Auto ML has enabled developers to harness state-of-the-art ML algorithms with minimal overhead. However, dur…
SPICE: An Automated SWE-Bench Labeling Pipeline for Issue Clarity, Test Coverage, and Effort Estimation
Gustavo A. Oliva, Gopi Krishnan Rajbahadur, Aaditya Bhatia +7
High-quality labeled datasets are crucial for training and evaluating foundation models in software engineering, but creating them is often prohibitively expensive and labor-intens…
RepoForge: Training a SOTA Fast-thinking SWE Agent with an End-to-End Data Curation Pipeline Synergizing SFT and RL at Scale
Zhilong Chen, Chengzong Zhao, Boyuan Chen +9
Training software engineering (SWE) LLMs is bottlenecked by expensive infrastructure, inefficient evaluation pipelines, scarce training data, and costly quality control. We present…