PEER: Expertizing Domain-Specific Tasks with a Multi-Agent Framework and Tuning Methods

In domain-specific applications, GPT-4, augmented with precise prompts or Retrieval- Augmented Generation (RAG), shows notable potential but faces the critical tri-lemma of performance, cost, and data privacy. High performance requires sophisticated processing techniques, yet managing multiple agents within a complex workflow often proves costly and challenging. To address this, we introduce the PEER (Plan, Execute, Express, Review) multiagent framework. This systematizes domain specific tasks by integrating precise question decomposition, advanced information retrieval, comprehensive summarization, and rigorous self-assessment. Given the concerns of cost and data privacy, enterprises are shifting from proprietary models like GPT-4 to custom models, striking a balance between cost, security, and performance.

we introduce the PEER (Plan, Execute, Express, Review) multiagent framework. This framework incorporates precise question decomposition, advanced information retrieval, comprehensive summarization, and rigorous self-assessment, aiming to streamline workflows and enhance problem-solving efficacy. Additionally, our research addresses enterprise demands for private deployment and stringent data privacy by developing industrial best practices that leverage online data and user feedback for effective model tuning.

With the advent of large models, we simulate the collaborative processes of human experts (e.g. financial) using multiple agents, achieving comparable interpretative results. This approach is encapsulated in the Plan, Execute, Express and Review (PEER) framework, where domain specific (e.g. financial) tasks are divided into these four steps. Each agent specializes in a single task, working together to accomplish the overall objective