A Learnable Agent Collaboration Network Framework for Personalized Multimodal AI Search Engine
On the map: Retrieval-augmented generation → Agentic RAG, agents and memory
also in 1 more
Abstract (arXiv)
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.
Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Placed in Agentic RAG, agents and memory, one of 15 directions in Retrieval-augmented generation. Builds on 23 of its 35 references that are in the map. First posted on arXiv 1 Sep 2024.
Builds on
23 of 35 references.
References · 23
- 2020Language Models are Few-Shot Learnerscited by 32,199
- 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
- 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
- 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,185
- 2015A large annotated corpus for learning natural language inferencecited by 1,837
- 2021Improving language models by retrieving from trillions of tokenscited by 1,278
- 2023ExpeL: LLM Agents Are Experiential Learnerscited by 814
- 2023LaMP: When Large Language Models Meet Personalizationcited by 425
- 2023Making Retrieval-Augmented Language Models Robust to Irrelevant Contextcited by 364
- 2022RARR: Researching and Revising What Language Models Say, Using Language Modelscited by 286
- 2023GPT4Tools: Teaching Large Language Model to Use Tools via Self-instructioncited by 245
- 2024MMedAgent: Learning to Use Medical Tools with Multi-modal Agentcited by 108
11 more
- 2022Long Time No See! Open-Domain Conversation with Long-Term Persona Memorycited by 107
- 2024Symbolic Learning Enables Self-Evolving Agentscited by 104
- 2023Lift Yourself Up: Retrieval-augmented Text Generation with Self Memorycited by 103
- 2023Personalisation within bounds: A risk taxonomy and policy framework for the alignment of large language models with personalised feedbackcited by 86
- 2023Let the LLMs Talk: Simulating Human-to-Human Conversational QA via Zero-Shot LLM-to-LLM Interactionscited by 70
- 2023Knowledge-Augmented Large Language Models for Personalized Contextual Query Suggestioncited by 43
- 2023Tree of Clarifications: Answering Ambiguous Questions with Retrieval-Augmented Large Language Modelscited by 42
- 2024Synthetic Dialogue Dataset Generation using LLM Agentscited by 39
- 2024Simulating Financial Market via Large Language Model based Agentscited by 25
- 2024Cognitive Personalized Search Integrating Large Language Models with an Efficient Memory Mechanismcited by 22
- 2024Enhancing Retrieval and Managing Retrieval: A Four-Module Synergy for Improved Quality and Efficiency in RAG Systemscited by 15
Built on by
Citing papers per year: 2024: 2; 2025: 3.
5 papers.
- 2025PersonaX: A Recommendation Agent Oriented User Modeling Framework for Long Behavior Sequencecited by 33
- 2024Personalized Multimodal Large Language Models: A Surveycited by 19
- 2024Self-Supervised Inference of Agents in Trustless Environmentscited by 1
- 2025MEGG: Replay via Maximally Extreme GGscore in Incremental Learning for Neural Recommendation Modelscited by 0
- 2025FUSE : Failure-aware Usage of Subagent Evidence for MultiModal Search and Recommendationcited by 0
- 2025FUSE : Failure-aware Usage of Subagent Evidence for MultiModal Search and Recommendation15 Nov 2025
- 2025MEGG: Replay via Maximally Extreme GGscore in Incremental Learning for Neural Recommendation Models9 Sep 2025
- 2025PersonaX: A Recommendation Agent Oriented User Modeling Framework for Long Behavior Sequence4 Mar 2025
- 2024Personalized Multimodal Large Language Models: A Survey3 Dec 2024
- 2024Self-Supervised Inference of Agents in Trustless Environments12 Sep 2024
Similar, not cited
Close in wording, no citation either way
- 2025HM-RAG: Hierarchical Multi-Agent Multimodal Retrieval Augmented Generation
- 2025Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG
- 2024Multimodal Query Suggestion with Multi-Agent Reinforcement Learning from Human Feedback
- 2025TURA: Tool-Augmented Unified Retrieval Agent for AI Search
- 2025QAgent: A modular Search Agent with Interactive Query Understanding
- 2024A Collaborative Multi-Agent Approach to Retrieval-Augmented Generation Across Diverse Data
- 2026A-RAG: Scaling Agentic Retrieval-Augmented Generation via Hierarchical Retrieval Interfaces
- 2025AgentMaster: A Multi-Agent Conversational Framework Using A2A and MCP Protocols for Multimodal Information Retrieval and Analysis