# Compiling Prompts, Not Crafting Them: A Reproducible Workflow for AI-Assisted Evidence Synthesis

arXiv: https://arxiv.org/abs/2509.00038 · HTML: https://mlsanity.com/paper/2509.00038/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 22 references that are in the map.
- First posted on arXiv 22 Aug 2025.

## Builds on (most cited first, 11 of 11)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting](https://mlsanity.com/paper/2310.11324/) (2023)
- [GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning](https://mlsanity.com/paper/2507.19457/) (2025)
- [Optimizing Instructions and Demonstrations for Multi-Stage Language Model Programs](https://mlsanity.com/paper/2406.11695/) (2024)
- [Benchmarking Prompt Sensitivity in Large Language Models](https://mlsanity.com/paper/2502.06065/) (2025)
- [Can large language models replace humans in the systematic review process? Evaluating GPT-4's efficacy in screening and extracting data from peer-reviewed and grey literature in multiple languages](https://mlsanity.com/paper/2310.17526/) (2023)
- [Automating Research Synthesis with Domain-Specific Large Language Model Fine-Tuning](https://mlsanity.com/paper/2404.08680/) (2024)
- [A Reproducibility and Generalizability Study of Large Language Models for Query Generation](https://mlsanity.com/paper/2411.14914/) (2024)
- [What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction](https://mlsanity.com/paper/2507.15152/) (2025)
- [Streamlining Systematic Reviews: A Novel Application of Large Language Models](https://mlsanity.com/paper/2412.15247/) (2024)
- [Efficacy of Large Language Models in Systematic Reviews](https://mlsanity.com/paper/2408.04646/) (2024)

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

- [Evaluating Prompting Strategies and Large Language Models in Systematic Literature Review Screening: Relevance and Task-Stage Classification](https://mlsanity.com/paper/2510.16091/) (2025)
- [Automated Risk-of-Bias Assessment of Randomized Controlled Trials: A First Look at a GEPA-trained Programmatic Prompting Framework](https://mlsanity.com/paper/2512.01452/) (2025)

## Abstract (arXiv)

Large language models (LLMs) offer significant potential to accelerate systematic literature reviews (SLRs), yet current approaches often rely on brittle, manually crafted prompts that compromise reliability and reproducibility. This fragility undermines scientific confidence in LLM-assisted evidence synthesis. In response, this work adapts recent advances in declarative prompt optimisation, developed for general-purpose LLM applications, and demonstrates their applicability to the domain of SLR automation. This research proposes a structured, domain-specific framework that embeds task declarations, test suites, and automated prompt tuning into a reproducible SLR workflow. These emerging methods are translated into a concrete blueprint with working code examples, enabling researchers to construct verifiable LLM pipelines that align with established principles of transparency and rigour in evidence synthesis. This is a novel application of such approaches to SLR pipelines.