CIIR@LiveRAG 2025: Optimizing Multi-Agent Retrieval Augmented Generation through Self-Training
By: Alireza Salemi, Mukta Maddipatla, Hamed Zamani
Potential Business Impact:
Helps AI answer hard questions by working together.
This paper presents mRAG, a multi-agent retrieval-augmented generation (RAG) framework composed of specialized agents for subtasks such as planning, searching, reasoning, and coordination. Our system uses a self-training paradigm with reward-guided trajectory sampling to optimize inter-agent collaboration and enhance response generation. Evaluated on DataMorgana-derived datasets during the SIGIR 2025 LiveRAG competition, mRAG outperforms conventional RAG baselines. We further analyze competition outcomes and showcase the framework's strengths with case studies, demonstrating its efficacy for complex, real-world RAG tasks.
Similar Papers
Efficient Agent: Optimizing Planning Capability for Multimodal Retrieval Augmented Generation
Artificial Intelligence
Helps AI understand current events better.
Improving Retrieval-Augmented Generation through Multi-Agent Reinforcement Learning
Computation and Language
Makes AI answer questions more truthfully.
HM-RAG: Hierarchical Multi-Agent Multimodal Retrieval Augmented Generation
Computation and Language
Helps computers answer harder questions using more information.