mlsanityData to 7 Oct 2026

Talk to Right Specialists: Iterative Routing in Multi-agent Systems for Question Answering

arXiv 2501.07813 ↗First posted 14 Jan 2025cs.MA cs.AI cs.CLcited by 6

On the map: Retrieval-augmented generation → Agentic RAG, agents and memory

Abstract (arXiv)

Retrieval-augmented generation (RAG) agents are increasingly deployed to answer questions over local knowledge bases that cannot be centralized due to knowledge-sovereignty constraints. This results in two recurring failures in production: users do not know which agent to consult, and complex questions require evidence distributed across multiple agents. To overcome these challenges, we propose RIRS, a training-free orchestration framework to enable a multi-agent system for question answering. In detail, RIRS summarizes each agent's local corpus in an embedding space, enabling a user-facing server to route queries only to the most relevant agents, reducing latency and avoiding noisy "broadcast-to-all" contexts. For complicated questions, the server can iteratively aggregate responses to derive intermediate results and refine the question to bridge the gap toward a comprehensive answer. Extensive experiments demonstrate the effectiveness of RIRS, including its ability to precisely select agents and provide accurate responses to single-hop queries, and its use of an iterative strategy to achieve accurate, multi-step resolutions for complex queries.

Key facts. Cited by 6 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 61 of its 88 references that are in the map. First posted on arXiv 14 Jan 2025.

Builds on

61 of 88 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024SLA Management in Reconfigurable Multi-Agent RAG: A Systems Approach to Question Answering7 Dec
  2. 2024REAPER: Reasoning based Retrieval Planning for Complex RAG Systems26 Jul

Other references · 59

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  3. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  4. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  5. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,767
  6. 2024Qwen2.5 Technical Reportcited by 4,713
  7. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  8. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  9. 2023Qwen Technical Reportcited by 3,273
  10. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  11. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,800
  12. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,761
38 more
  1. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,739
  2. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Societycited by 1,348
  3. 2023Gorilla: Large Language Model Connected with Massive APIscited by 1,302
  4. 2021Improving language models by retrieving from trillions of tokenscited by 1,278
  5. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,259
  6. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,203
  7. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,203
  8. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,103
  9. 2022Measuring and Narrowing the Compositionality Gap in Language Modelscited by 1,054
  10. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 911
  11. 2021MuSiQue: Multihop Questions via Single-hop Question Compositioncited by 893
  12. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 786
  13. 2017Reading Wikipedia to Answer Open-Domain Questionscited by 777
  14. 2024Large Language Model based Multi-Agents: A Survey of Progress and Challengescited by 752
  15. 2024RouteLLM: Learning to Route LLMs with Preference Datacited by 633
  16. 2023AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviorscited by 580
  17. 2023Active Retrieval Augmented Generationcited by 506
  18. 2023Chameleon: Plug-and-Play Compositional Reasoning with Large Language Modelscited by 352
  19. 2023Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergycited by 343
  20. 2024Benchmarking Retrieval-Augmented Generation for Medicinecited by 326
  21. 2024MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queriescited by 253
  22. 2022RealTime QA: What's the Answer Right Now?cited by 239
  23. 2024mGTE: Generalized Long-Context Text Representation and Reranking Models for Multilingual Text Retrievalcited by 233
  24. 2023Query Rewriting for Retrieval-Augmented Large Language Modelscited by 211
  25. 2023AutoAgents: A Framework for Automatic Agent Generationcited by 211
  26. 2024RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMscited by 200
  27. 2024Corrective Retrieval Augmented Generationcited by 187
  28. 2024EASYTOOL: Enhancing LLM-based Agents with Concise Tool Instructioncited by 153
  29. 2024RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generationcited by 144
  30. 2023Routing to the Expert: Efficient Reward-guided Ensemble of Large Language Modelscited by 141
  31. 2024AgentScope: A Flexible yet Robust Multi-Agent Platformcited by 120
  32. 2023Retrieval meets Long Context Large Language Modelscited by 114
  33. 2024RouterDC: Query-Based Router by Dual Contrastive Learning for Assembling Large Language Modelscited by 84
  34. 2024FedBiOT: LLM Local Fine-tuning in Federated Learning without Full Modelcited by 73
  35. 2024Retrieval-Augmented Generation for Natural Language Processing: A Surveycited by 70
  36. 2024MindSearch: Mimicking Human Minds Elicits Deep AI Searchercited by 65
  37. 2024DRAGIN: Dynamic Retrieval Augmented Generation based on the Information Needs of Large Language Modelscited by 63
  38. 2023LLatrieval: LLM-Verified Retrieval for Verifiable Generationcited by 52

50 most cited of 59 All 59 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 4.

6 papers.

  1. 2026A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agentscited by 47
  2. 2026StateBridge: Training-free Hidden-state Alignment for Latent Communication in LLM Multi-Agent Systemscited by 5
  3. 2025PORTool: Importance-Aware Policy Optimization with Rewarded Tree for Multi-Tool-Integrated Reasoningcited by 4
  4. 2025BELLE: A Bi-Level Multi-Agent Reasoning Framework for Multi-Hop Question Answeringcited by 3
  5. 2026EARS: Explanatory Abstention for Reliable Sub-Agent Modeling in Large-scale Multi-Agent Systemscited by 1
  6. 2026AdaSTORM: Scaling LLM Reasoning on Dynamic Graphs via Adaptive Spatio-Temporal Multi-Agent Collaborationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Dissecting Agentic RAG: A Component Ablation for Multi-Hop QA with a Local 7B Model
  2. 2026Agentic-R: Learning to Retrieve for Agentic Search
  3. 2025MAO-ARAG: Multi-Agent Orchestration for Adaptive Retrieval-Augmented Generation
  4. 2024Dynamic Multi-Agent Orchestration and Retrieval for Multi-Source Question-Answer Systems using Large Language Models
  5. 2025Learning to Route: A Rule-Driven Agent Framework for Hybrid-Source Retrieval-Augmented Generation
  6. 2026PRISMA: Reinforcement Learning Guided Two-Stage Policy Optimization in Multi-Agent Architecture for Open-Domain Multi-Hop Question Answering
  7. 2026EvolveRouter: Co-Evolving Routing and Prompt for Multi-Agent Question Answering
  8. 2025MA-RAG: Multi-Agent Retrieval-Augmented Generation via Collaborative Chain-of-Thought Reasoning