# From Articles to Code: On-Demand Generation of Core Algorithms from Scientific Publications

arXiv: https://arxiv.org/abs/2507.22324 · HTML: https://mlsanity.com/paper/2507.22324/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 22 references that are in the map.
- First posted on arXiv 30 Jul 2025.

## Builds on (most cited first, 5 of 5)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Competition-Level Code Generation with AlphaCode](https://mlsanity.com/paper/2203.07814/) (2022)
- [What Prompts Don't Say: Understanding and Managing Underspecification in LLM Prompts](https://mlsanity.com/paper/2505.13360/) (2025)
- [Analyzing Maintenance Activities of Software Libraries](https://mlsanity.com/paper/2306.06030/) (2023)

## Built on by (most cited first, 2 of 2)

- [Paper2Agent: Reimagining Research Papers As Interactive and Reliable AI Agents](https://mlsanity.com/paper/2509.06917/) (2025)
- [Which Algorithm Specification Formats Help Language Models Implement Machine Learning Algorithms?](https://mlsanity.com/paper/2607.03158/) (2026)

## Abstract (arXiv)

Maintaining software packages imposes significant costs due to dependency management, bug fixes, and versioning. We show that rich method descriptions in scientific publications can serve as standalone specifications for modern large language models (LLMs), enabling on-demand code generation that could supplant human-maintained libraries. We benchmark state-of-the-art models (GPT-o4-mini-high, Gemini Pro 2.5, Claude Sonnet 4) by tasking them with implementing a diverse set of core algorithms drawn from original publications. Our results demonstrate that current LLMs can reliably reproduce package functionality with performance indistinguishable from conventional libraries. These findings foreshadow a paradigm shift toward flexible, on-demand code generation and away from static, human-maintained packages, which will result in reduced maintenance overhead by leveraging published articles as sufficient context for the automated implementation of analytical workflows.