A multi-agent RAG framework trained by self-supervision on high-reward interaction trajectories outperforms a vanilla RAG baseline on DataMorgana-generated questions and places 7th in the LiveRAG 2025 competition.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
CIIR@LiveRAG 2025: Optimizing Multi-Agent Retrieval Augmented Generation through Self-Training
A multi-agent RAG framework trained by self-supervision on high-reward interaction trajectories outperforms a vanilla RAG baseline on DataMorgana-generated questions and places 7th in the LiveRAG 2025 competition.