Stdlib or Third-Party? Empirical Performance and Correctness of LLM-Assisted Zero-Dependency Python Libraries
cs.SE, cs.AI, cs.PL
Submitted: 2026-05-20
Updated: 2026-10-13
Code: https://github.com/Oaklight/zerodep
Project page: https://oaklight.github.io/zerodep
Terminology
Sources
- How Deep Does Your Dependency Tree Go? An Empirical Study of Dependency Amplification Across 10 Package Ecosystems
- Machine Learning Systems are Bloated and Vulnerable
- We Have a Package for You! A Comprehensive Analysis of Package Hallucinations by Code Generating LLMs
- An Empirical Study of Vulnerable Package Dependencies in LLM Repositories
- Commit0: Library Generation from Scratch
- RepoZero: Can LLMs Generate a Code Repository from Scratch?
Related papers
- Falsification-Based Verification of LLM-Generated Optimization Models: Sound Test Batteries and Their Detection Limits
- GitSkills: A Dataset of Agent Skills on GitHub
- SABER: Benchmarking Operational Safety of LLM Coding Agents in Stateful Project Workspaces
- PackMonitor: Enabling Zero Package Hallucinations Through Decoding-Time Monitoring
- IntentCoding: Amplifying User Intent in Code Generation
- Incentives and Outcomes in Bug Bounties