arXiv:2509.05764v1 Announce Type: new Abstract: With the evolution of generative AI, multi – agent systems leveraging large – language models(LLMs) have emerged as a powerful tool for complex tasks. However, these systems face challenges in quantifying agent performance and lack mechanisms to assess agent credibility. To address these issues, we introduce DRF, a dynamic reputation filtering framework. DRF constructs an interactive rating network to quantify agent performance, designs a reputation scoring mechanism to measure agent honesty and capability, and integrates an Upper Confidence Bound – based strategy to enhance agent selection efficiency. Experiments show that DRF significantly improves task completion quality and collaboration efficiency in logical reasoning and code – generation tasks, offering a new approach for multi – agent systems to handle large – scale tasks.
Original: https://arxiv.org/abs/2509.05764