# Evolving Prompts In-Context: An Open-ended, Self-replicating Perspective

arXiv: https://arxiv.org/abs/2506.17930 · HTML: https://mlsanity.com/paper/2506.17930/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Jun 2025.

## Built on by (most cited first, 8 of 8)

- [Federation over Text: Insight Sharing for Multi-Agent Reasoning](https://mlsanity.com/paper/2604.16778/) (2026)
- [PIAST: Rapid Prompting with In-context Augmentation for Scarce Training data](https://mlsanity.com/paper/2512.11013/) (2025)
- [Knowledge-Centric Self-Improvement](https://mlsanity.com/paper/2607.19592/) (2026)
- [TATRA: Training-Free Instance-Adaptive Prompting Through Rephrasing and Aggregation](https://mlsanity.com/paper/2603.03298/) (2026)
- [DiffuMask: Diffusion Language Model for Token-level Prompt Pruning](https://mlsanity.com/paper/2604.06627/) (2026)
- [Automated Reformulation of Robust Optimization via Memory-Augmented Large Language Models](https://mlsanity.com/paper/2605.11813/) (2026)
- [Learning Evidence Highlighting for Frozen LLMs](https://mlsanity.com/paper/2604.22565/) (2026)
- [Probabilistic Concept-Aware Steering for Trustworthy LLM Inference](https://mlsanity.com/paper/2607.18259/) (2026)

## Abstract (arXiv)

We propose a novel prompt design paradigm that challenges conventional wisdom in large language model (LLM) prompting. While conventional wisdom prioritizes well-crafted instructions and demonstrations for in-context learning (ICL), we show that pruning random demonstrations into seemingly incoherent "gibberish" can remarkably improve performance across diverse tasks. Notably, the "gibberish" always matches or surpasses state-of-the-art automatic prompt optimization techniques, achieving substantial gains regardless of LLM alignment. Nevertheless, discovering an effective pruning strategy is non-trivial, as existing attribution methods and prompt compression algorithms fail to deliver robust results, let alone human intuition. In terms of this, we propose a self-discover prompt optimization framework, PromptQuine, an evolutionary search framework that automatically searches for the pruning strategy by itself using only low-data regimes. Much like the emergent complexity in nature--such as symbiosis and self-organization--arising in response to resource constraints, our framework evolves and refines unconventional yet highly effective prompts by leveraging only the tokens present within the context. We demonstrate its effectiveness across classification, multi-choice question answering, generation and math reasoning tasks across LLMs, while achieving decent runtime efficiency. We hope our findings can guide mechanistic studies on in-context learning, and provide a call to action, to pave the way for more open-ended search algorithms for more effective LLM prompting.