# MA-RAG: Multi-Agent Retrieval-Augmented Generation via Collaborative Chain-of-Thought Reasoning

arXiv: https://arxiv.org/abs/2505.20096 · HTML: https://mlsanity.com/paper/2505.20096/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning.
- Builds on 28 of its 109 references that are in the map.
- First posted on arXiv 26 May 2025.

## Placed in

- LLM reasoning / [Knowledge- and tool-augmented reasoning](https://mlsanity.com/lr/knowledge-and-tool-augmented-reasoning/)
- Retrieval-augmented generation / [Agentic RAG, agents and memory](https://mlsanity.com/rag/agentic-rag-agents-and-memory/)
- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 28 of 28)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions](https://mlsanity.com/paper/2311.05232/) (2023)
- [Gemini: A Family of Highly Capable Multimodal Models](https://mlsanity.com/paper/2312.11805/) (2023)
- [Measuring short-form factuality in large language models](https://mlsanity.com/paper/2411.04368/) (2024)
- [Teaching language models to support answers with verified quotes](https://mlsanity.com/paper/2203.11147/) (2022)
- [A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration](https://mlsanity.com/paper/2310.02170/) (2023)
- [HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models](https://mlsanity.com/paper/2405.14831/) (2024)
- [MEDITRON-70B: Scaling Medical Pretraining for Large Language Models](https://mlsanity.com/paper/2311.16079/) (2023)
- [RAFT: Adapting Language Model to Domain Specific RAG](https://mlsanity.com/paper/2403.10131/) (2024)
- [RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMs](https://mlsanity.com/paper/2407.02485/) (2024)
- [KronA: Parameter Efficient Tuning with Kronecker Adapter](https://mlsanity.com/paper/2212.10650/) (2022)
- [NoLiMa: Long-Context Evaluation Beyond Literal Matching](https://mlsanity.com/paper/2502.05167/) (2025)
- [A Comprehensive Survey on Long Context Language Modeling](https://mlsanity.com/paper/2503.17407/) (2025)
- [ProAgent: Building Proactive Cooperative Agents with Large Language Models](https://mlsanity.com/paper/2308.11339/) (2023)
- [ChatQA: Surpassing GPT-4 on Conversational QA and RAG](https://mlsanity.com/paper/2401.10225/) (2024)
- [A Multi-Task Embedder For Retrieval Augmented LLMs](https://mlsanity.com/paper/2310.07554/) (2023)
- [Open Deep Search: Democratizing Search with Open-source Reasoning Agents](https://mlsanity.com/paper/2503.20201/) (2025)
- [Reinforcement Learning for Optimizing RAG for Domain Chatbots](https://mlsanity.com/paper/2401.06800/) (2024)
- [Adapting LLM Agents with Universal Feedback in Communication](https://mlsanity.com/paper/2310.01444/) (2023)
- [Agentic Retrieval-Augmented Generation for Time Series Analysis](https://mlsanity.com/paper/2408.14484/) (2024)
- [CollEX -- A Multimodal Agentic RAG System Enabling Interactive Exploration of Scientific Collections](https://mlsanity.com/paper/2504.07643/) (2025)

## Built on by (most cited first, 26 of 26)

- [Memory in the Age of AI Agents](https://mlsanity.com/paper/2512.13564/) (2025)
- [A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges](https://mlsanity.com/paper/2508.05668/) (2025)
- [A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agents](https://mlsanity.com/paper/2601.12538/) (2026)
- [SoK: Agentic Retrieval-Augmented Generation (RAG): Taxonomy, Architectures, Evaluation, and Research Directions](https://mlsanity.com/paper/2603.07379/) (2026)
- [Benefits and Limitations of Communication in Multi-Agent Reasoning](https://mlsanity.com/paper/2510.13903/) (2025)
- [Interact-RAG: Reason and Interact with the Corpus, Beyond Black-Box Retrieval](https://mlsanity.com/paper/2510.27566/) (2025)
- [From Virtual Agents to Robot Teams: A Multi-Robot Framework Evaluation in High-Stakes Healthcare Context](https://mlsanity.com/paper/2506.03546/) (2025)
- [Retrieval Augmented Generation (RAG) for Fintech: Agentic Design and Evaluation](https://mlsanity.com/paper/2510.25518/) (2025)
- [MATA: A Trainable Hierarchical Automaton System for Multi-Agent Visual Reasoning](https://mlsanity.com/paper/2601.19204/) (2026)
- [Experience as a Compass: Multi-agent RAG with Evolving Orchestration and Agent Prompts](https://mlsanity.com/paper/2604.00901/) (2026)
- [Only Ask What You Don't Know: Grounded Delta Planning for Efficient Multi-step RAG](https://mlsanity.com/paper/2606.22681/) (2026)
- [Confident RAG: Enhancing the Performance of LLMs for Mathematics Question Answering through Multi-Embedding and Confidence Scoring](https://mlsanity.com/paper/2507.17442/) (2025)
- [REX-RAG: Reasoning Exploration with Policy Correction in Retrieval-Augmented Generation](https://mlsanity.com/paper/2508.08149/) (2025)
- [Mitigating Hallucination in Large Language Models (LLMs): An Application-Oriented Survey on RAG, Reasoning, and Agentic Systems](https://mlsanity.com/paper/2510.24476/) (2025)
- [Rethinking Agentic RAG: Toward LLM-Driven Logical Retrieval Beyond Embeddings](https://mlsanity.com/paper/2605.27123/) (2026)
- [EvoEmbedding: Evolvable Representations for Long-Context Retrieval and Agentic Memory](https://mlsanity.com/paper/2606.21649/) (2026)
- [MedCoAct: Confidence-Aware Multi-Agent Collaboration for Complete Clinical Decision](https://mlsanity.com/paper/2510.10461/) (2025)
- [An Agentic AI Framework with Large Language Models and Chain-of-Thought for UAV-Assisted Logistics Scheduling with Mobile Edge Computing](https://mlsanity.com/paper/2605.13221/) (2026)
- [FLOWREADER: Min-Cost Flow Optimization for Multi-Modal Long Document Q&A](https://mlsanity.com/paper/2606.07235/) (2026)
- [Multi-Dimensional Knowledge Profiling with Large-Scale Literature Database and Hierarchical Retrieval](https://mlsanity.com/paper/2601.15170/) (2026)
- [AI Engineering Blueprint for On-Premises Retrieval-Augmented Generation Systems](https://mlsanity.com/paper/2604.01395/) (2026)
- [Constraint-Aware Hierarchical Search for Regulation-Driven Fine-Grained Classification](https://mlsanity.com/paper/2607.10588/) (2026)
- [Towards Trustworthy and Cost-Efficient Data Integration: From Na"ive RAG to Agentic RAG](https://mlsanity.com/paper/2607.22319/) (2026)
- [Re-ranking and Late Interaction Drive Retrieval Quality: A Controlled Comparison of RAG Strategies for Scientific Question Answering](https://mlsanity.com/paper/2609.38473/) (2026)
- [Unanimously Wrong: Certified Abstention from How Medical LLM Consensus Forms](https://mlsanity.com/paper/2610.07570/) (2026)
- [PANINI-DR: Controlled Deep Research through Generative Semantic Workspaces](https://mlsanity.com/paper/2610.15208/) (2026)

## Abstract (arXiv)

We present MA-RAG, a Multi-Agent framework for Retrieval-Augmented Generation (RAG) that addresses the inherent ambiguities and reasoning challenges in complex information-seeking tasks. Unlike conventional RAG methods that rely on end-to-end fine-tuning or isolated component enhancements, MA-RAG orchestrates a collaborative set of specialized AI agents: Planner, Step Definer, Extractor, and QA Agents, each responsible for a distinct stage of the RAG pipeline. By decomposing tasks into subtasks such as query disambiguation, evidence extraction, and answer synthesis, and enabling agents to communicate intermediate reasoning via chain-of-thought prompting, MA-RAG progressively refines retrieval and synthesis while maintaining modular interpretability. Extensive experiments on multi-hop and ambiguous QA benchmarks, including NQ, HotpotQA, 2WikimQA, and TriviaQA, demonstrate that MA-RAG significantly outperforms standalone LLMs and existing RAG methods across all model scales. Notably, even a small LLaMA3-8B model equipped with MA-RAG surpasses larger standalone LLMs, while larger variants (LLaMA3-70B and GPT-4o-mini) set new state-of-the-art results on challenging multi-hop datasets. Ablation studies reveal that both the planner and extractor agents are critical for multi-hop reasoning, and that high-capacity models are especially important for the QA agent to synthesize answers effectively. Beyond general-domain QA, MA-RAG generalizes to specialized domains such as medical QA, achieving competitive performance against domain-specific models without any domain-specific fine-tuning. Our results highlight the effectiveness of collaborative, modular reasoning in retrieval-augmented systems: MA-RAG not only improves answer accuracy and robustness but also provides interpretable intermediate reasoning steps, establishing a new paradigm for efficient and reliable multi-agent RAG.