AgentRec: Agent Recommendation Using Sentence Embeddings Aligned to Human Feedback

Understand

Multi-agent systems must decide which agent is the most appropriate for a given task.

• We propose a novel architecture for recommending which LLM agent out of many should perform a task given a natural language prompt by extending the Sentence-BERT (SBERT) encoder model.
• On test data, we are able to achieve a top-1 accuracy of 92.2% with each classification taking less than 300 milliseconds.
• In contrast to traditional classification methods, our architecture is computationally cheap, adaptive to new classes, interpretable, and controllable with arbitrary metrics through reinforcement learning.