SLA Management in Reconfigurable Multi-Agent RAG: A Systems Approach to Question Answering
On the map: LLM reasoning → Knowledge- and tool-augmented reasoning
also in 2 more
Abstract (arXiv)
Retrieval Augmented Generation (RAG) enables Large Language Models (LLMs) to generalize to new information by decoupling reasoning capabilities from static knowledge bases. Traditional RAG enhancements have explored vertical scaling-assigning subtasks to specialized modules-and horizontal scaling-replicating tasks across multiple agents-to improve performance. However, real-world applications impose diverse Service Level Agreements (SLAs) and Quality of Service (QoS) requirements, involving trade-offs among objectives such as reducing cost, ensuring answer quality, and adhering to specific operational constraints. In this work, we present a systems-oriented approach to multi-agent RAG tailored for real-world Question Answering (QA) applications. By integrating task-specific non-functional requirements-such as answer quality, cost, and latency-into the system, we enable dynamic reconfiguration to meet diverse SLAs. Our method maps these Service Level Objectives (SLOs) to system-level parameters, allowing the generation of optimal results within specified resource constraints. We conduct a case study in the QA domain, demonstrating how dynamic re-orchestration of a multi-agent RAG system can effectively manage the trade-off between answer quality and cost. By adjusting the system based on query intent and operational conditions, we systematically balance performance and resource utilization. This approach allows the system to meet SLOs for various query types, showcasing its practicality for real-world applications.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 11 of its 28 references that are in the map. First posted on arXiv 7 Dec 2024.
Builds on
11 of 28 references.
Closest ancestors · 1
Same direction, newest first
Other references · 10
- 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
- 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
- 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,739
- 2020MPNet: Masked and Permuted Pre-training for Language Understandingcited by 973
- 2016Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphscited by 853
- 2023Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergycited by 343
- 2024PlanRAG: A Plan-then-Retrieval Augmented Generation for Generative Large Language Models as Decision Makerscited by 42
- 2024Modular RAG: Transforming RAG Systems into LEGO-like Reconfigurable Frameworkscited by 41
- 2024When Large Language Models Meet Vector Databases: A Surveycited by 39
- 2024Retrieve-Plan-Generation: An Iterative Planning and Answering Framework for Knowledge-Intensive LLM Generationcited by 15
Built on by
Citing papers per year: 2025: 3.
3 papers.
Similar, not cited
Close in wording, no citation either way
- 2025MAO-ARAG: Multi-Agent Orchestration for Adaptive Retrieval-Augmented Generation
- 2024Dynamic Multi-Agent Orchestration and Retrieval for Multi-Source Question-Answer Systems using Large Language Models
- 2025RAGCap-Bench: Benchmarking Capabilities of LLMs in Agentic Retrieval Augmented Generation Systems
- 2025Agent-UniRAG: A Trainable Open-Source LLM Agent Framework for Unified Retrieval-Augmented Generation Systems
- 2026Dissecting Agentic RAG: A Component Ablation for Multi-Hop QA with a Local 7B Model
- 2024Beyond-RAG: Question Identification and Answer Generation in Real-Time Conversations
- 2026SPD-RAG: Sub-Agent Per Document Retrieval-Augmented Generation
- 2025HM-RAG: Hierarchical Multi-Agent Multimodal Retrieval Augmented Generation