DRF: LLM-AGENT Dynamic Reputation Filtering Framework
This addresses the challenge of agent credibility and performance assessment in multi-agent systems for AI researchers and developers, though it appears incremental as it builds on existing reputation and selection strategies.
The paper tackles the problem of quantifying agent performance and assessing credibility in multi-agent systems using large language models, introducing DRF, a dynamic reputation filtering framework that significantly improves task completion quality and collaboration efficiency in logical reasoning and code-generation tasks.
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.