Supplementary material and code for the paper:
"Towards Automating Software Development: An Empirical Assessment of Multi-Agent Frameworks"
| Component | Description |
|---|---|
| swe-bench-lite-api | Service providing bug-fixing tasks & metadata (REST API). |
| swe-bench-lite-tester | Execution environment to validate patches (Dockerized). |
| mas_metrics | Definitions of metrics used for evaluation. |
| questionnaires | Original PDF questionnaires from the user study. |