Single LLM, Multiple Roles: A Unified Retrieval-Augmented Generation Framework Using Role-Specific Token Optimization

Existing studies have optimized retrievalaugmented generation (RAG) across various sub-tasks, such as query understanding and retrieval refinement, but integrating these optimizations into a unified framework remains challenging. To tackle this problem, this work proposes RoleRAG, a unified RAG framework that achieves efficient multi-task processing through role-specific token optimization. RoleRAG comprises six modules, each handling a specific sub-task within the RAG process. Additionally, we introduce a query graph to represent the decomposition of the query, which can be dynamically resolved according to the decomposing state. All modules are driven by the same underlying LLM, distinguished by task-specific role tokens that are individually optimized. This design allows RoleRAG to dynamically activate different modules within a single LLM instance, thereby streamlining deployment and reducing resource consumption. Experimental results on five open-domain question-answering datasets demonstrate the effectiveness, generalizability, and flexibility of our framework. * Corresponding author. (c) RoleRAG, a unified RAG framework LLM Role token 1 Query Graph Builder Role token 2 Retrieval Judge Role token n Answer Reasoner … Query (a) Optimizing individual modules (e.g., query rewriter) LLM Query rewrite reflect Retriever Answer generation reflect (b) Learning all modules jointly via self-reflection (e.g., Self-RAG)