# C-Evolve: Consensus-based Evolution for Prompt Groups

arXiv: https://arxiv.org/abs/2509.23331 · HTML: https://mlsanity.com/paper/2509.23331/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Sep 2025.

## Built on by (most cited first, 5 of 5)

- [The FM Agent](https://mlsanity.com/paper/2510.26144/) (2025)
- [SeaEvo: Advancing Algorithm Discovery with Strategy Space Evolution](https://mlsanity.com/paper/2604.24372/) (2026)
- [What Do Evolutionary Coding Agents Evolve?](https://mlsanity.com/paper/2605.20086/) (2026)
- [A Training-Free Guess What Vision Language Model from Snippets to Open-Vocabulary Object Detection](https://mlsanity.com/paper/2601.11910/) (2026)
- [What Should the Reflector See? An Empirical Study of Evidence in Reflective Prompt Optimization](https://mlsanity.com/paper/2609.32452/) (2026)

## Abstract (arXiv)

Prompt evolution algorithms offer a powerful paradigm for enhancing AI systems based on closed-source models, while few work explores whether aggregating results from multiple prompts to reach a consensus can further advance the system capability boundary. In this paper, we introduce Consensus-Evolve (C-Evolve), an evolutionary algorithm that discovers a group of prompts whose aggregated outputs after majority voting achieve optimal performance. More specifically, C-Evolve employs an island-based evolutionary algorithm to maintain population diversity, and prompts from distinct islands are selected to form groups to aggregate their outputs. The key difference from single individual evolution is a voting score, which evaluates each individual prompt's contribution within groups. We take this as the fitness score for evolution instead of individual performance. Consequently, C-Evolve is more likely to produce and maintain prompts with higher potential to form a high-performing group and eliminate low-performing ones, gradually improving the group performance after reaching consensus. Our method achieves state-of-the-art performance across a wide range of tasks, including both open-ended tasks like HotpotQA and closed-ended tasks like MATH. On Qwen3-8B, C-Evolve achieves 70.67% on HotpotQA and 43.88% on IFBench, which are 4.95% and 2.73% higher than GEPA, respectively. For GPT-4.1-mini, the accuracy on IFBench is further improved to 47.96% and reaches 95.33% in the MATH benchmark. These results demonstrate the C-Evolve's competitive performance.