C-Evolve: Consensus-based Evolution for Prompt Groups

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. INTRODUCTION The advancement of Large Language Models (LLMs) has significantly accelerated progress in natural language processing (Liu et al., 2024; Thirunavukarasu et al., 2023) . However, many state-of-theart models, such as GPT-4.1 (OpenAI, 2025) and Claude (Anthropic, 2024), remain closed-source and are accessible only via API interfaces. This restricts researchers from performing parameter fine-tuning to adapt these models to specific downstream tasks. To leverage the capabilities of such black-box models, a new paradigm prompt-based optimization methods have emerged (Opsahl-Ong et al.