A Learnable Agent Collaboration Network Framework for Personalized Multimodal AI Search Engine

TL;DR

This paper introduces the Agent Collaboration Network framework for personalized multimodal AI search engines, enabling specialized agents to collaboratively improve response quality, personalization, and adaptability through online learning and dynamic interactions.

Contribution

It proposes a novel multi-agent framework with mechanisms for multimodal understanding and online evolution, including a Reflective Forward Optimization method for real-time system adaptation.

Findings

Enhanced response quality and personalization in AI search

Improved online learning and adaptation capabilities

Potential applicability of the optimization method to other agent systems

Abstract

Large language models (LLMs) and retrieval-augmented generation (RAG) techniques have revolutionized traditional information access, enabling AI agent to search and summarize information on behalf of users during dynamic dialogues. Despite their potential, current AI search engines exhibit considerable room for improvement in several critical areas. These areas include the support for multimodal information, the delivery of personalized responses, the capability to logically answer complex questions, and the facilitation of more flexible interactions. This paper proposes a novel AI Search Engine framework called the Agent Collaboration Network (ACN). The ACN framework consists of multiple specialized agents working collaboratively, each with distinct roles such as Account Manager, Solution Strategist, Information Manager, and Content Creator. This framework integrates mechanisms for picture content understanding, user profile tracking, and online evolution, enhancing the AI search engine's response quality, personalization, and interactivity. A highlight of the ACN is the introduction of a Reflective Forward Optimization method (RFO), which supports the online synergistic adjustment among agents. This feature endows the ACN with online learning capabilities, ensuring that the system has strong interactive flexibility and can promptly adapt to user feedback. This learning method may also serve as an optimization approach for agent-based systems, potentially influencing other domains of agent applications.