mlsanityData to 7 Oct 2026

ATM: Adversarial Tuning Multi-agent System Makes a Robust Retrieval-Augmented Generator

arXiv 2405.18111 ↗First posted 28 May 2024cs.CLcited by 19

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

also in 1 more
Abstract (arXiv)

Large language models (LLMs) are proven to benefit a lot from retrieval-augmented generation (RAG) in alleviating hallucinations confronted with knowledge-intensive questions. RAG adopts information retrieval techniques to inject external knowledge from semantic-relevant documents as input contexts. However, since today's Internet is flooded with numerous noisy and fabricating content, it is inevitable that RAG systems are vulnerable to these noises and prone to respond incorrectly. To this end, we propose to optimize the retrieval-augmented Generator with an Adversarial Tuning Multi-agent system (ATM). The ATM steers the Generator to have a robust perspective of useful documents for question answering with the help of an auxiliary Attacker agent through adversarially tuning the agents for several iterations. After rounds of multi-agent iterative tuning, the Generator can eventually better discriminate useful documents amongst fabrications. The experimental results verify the effectiveness of ATM and we also observe that the Generator can achieve better performance compared to the state-of-the-art baselines.

Key facts. Cited by 19 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 44 of its 68 references that are in the map. First posted on arXiv 28 May 2024.

Builds on

44 of 68 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024RAT: Retrieval Augmented Thoughts Elicit Context-Aware Reasoning in Long-Horizon Generation8 Mar

Other references · 43

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2022Training language models to follow instructions with human feedbackcited by 15,712
  3. 2017Proximal Policy Optimization Algorithmscited by 14,441
  4. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  5. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  6. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  7. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  8. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,767
  9. 2022Generative Adversarial Networkscited by 5,603
  10. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  11. 2022FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awarenesscited by 3,611
  12. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
31 more
  1. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,895
  2. 2023FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioningcited by 2,551
  3. 2017Billion-scale similarity search with GPUscited by 2,477
  4. 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,168
  5. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,800
  6. 2016MS MARCO: A Human Generated MAchine Reading COmprehension Datasetcited by 1,591
  7. 2019ZeRO: Memory Optimizations Toward Training Trillion Parameter Modelscited by 1,278
  8. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,103
  9. 2023Large Language Models Can Be Easily Distracted by Irrelevant Contextcited by 820
  10. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 786
  11. 2022A Survey on In-context Learningcited by 717
  12. 2019Latent Retrieval for Weakly Supervised Open Domain Question Answeringcited by 691
  13. 2024Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Modelscited by 552
  14. 2022Precise Zero-Shot Dense Retrieval without Relevance Labelscited by 508
  15. 2024NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Modelscited by 466
  16. 2024Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexitycited by 437
  17. 2024LLM2Vec: Large Language Models Are Secretly Powerful Text Encoderscited by 396
  18. 2023Making Retrieval-Augmented Language Models Robust to Irrelevant Contextcited by 364
  19. 2023Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervisioncited by 318
  20. 2024The Power of Noise: Redefining Retrieval for RAG Systemscited by 275
  21. 2024RAFT: Adapting Language Model to Domain Specific RAGcited by 258
  22. 2019A Study of BFLOAT16 for Deep Learning Trainingcited by 227
  23. 2024Generative Representational Instruction Tuningcited by 227
  24. 2023RA-DIT: Retrieval-Augmented Dual Instruction Tuningcited by 194
  25. 2024Certifiably Robust RAG against Retrieval Corruptioncited by 144
  26. 2017Adversarial Learning for Neural Dialogue Generationcited by 103
  27. 2023Large Language Models Suffer From Their Own Output: An Analysis of the Self-Consuming Training Loopcited by 75
  28. 2024Rejection Improves Reliability: Training LLMs to Refuse Unknown Questions Using RL from Knowledge Feedbackcited by 64
  29. 2018DSGAN: Generative Adversarial Training for Distant Supervision Relation Extractioncited by 23
  30. 2024Spiral of Silence: How is Large Language Model Killing Information Retrieval? -- A Case Study on Open Domain Question Answeringcited by 5
  31. 2021Progressive Adversarial Learning for Bootstrapping: A Case Study on Entity Set Expansioncited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 11; 2026: 7.

19 papers.

Sort:

By area:

  1. 2025A Survey on the Optimization of Large Language Model-based Agentscited by 45
  2. 2025Improving Retrieval-Augmented Generation through Multi-Agent Reinforcement Learningcited by 39
  3. 2025AgentArmor: Enforcing Program Analysis on Agent Runtime Trace to Defend Against Prompt Injectioncited by 39
  4. 2024PA-RAG: RAG Alignment via Multi-Perspective Preference Optimizationcited by 11
  5. 2025Iterative Self-Incentivization Empowers Large Language Models as Agentic Searcherscited by 11
  6. 2025Direct Retrieval-augmented Optimization: Synergizing Knowledge Selection and Language Modelscited by 9
  7. 2025Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrievalcited by 7
  8. 2026SoK: Privacy Risks and Mitigations in Retrieval-Augmented Generation Systemscited by 7
  9. 2026Stable-RAG: Mitigating Retrieval-Permutation-Induced Hallucinations in Retrieval-Augmented Generationcited by 5
  10. 2025RAGentA: Multi-Agent Retrieval-Augmented Generation for Attributed Question Answeringcited by 4
  11. 2026MagicAgent: Towards Generalized Agent Planningcited by 2
  12. 2026Experience as a Compass: Multi-agent RAG with Evolving Orchestration and Agent Promptscited by 2
7 more
  1. 2026Securing Retrieval-Augmented Generation: A Taxonomy of Attacks, Defenses, and Future Directionscited by 2
  2. 2025Bridging the Capability Gap: Joint Alignment Tuning for Harmonizing LLM-based Multi-Agent Systemscited by 1
  3. 2025On the Diminishing Returns of Complex Robust RAG Training in the Era of Powerful LLMscited by 0
  4. 2025MoK-RAG: Mixture of Knowledge Paths Enhanced Retrieval-Augmented Generation for Embodied AI Environmentscited by 0
  5. 2025Can Synthetic Query Rewrites Capture User Intent Better than Humans in Retrieval-Augmented Generation?cited by 0
  6. 2026Runtime Burden Allocation for Structured LLM Routing in Agentic Expert Systems: A Full-Factorial Cross-Backend Methodologycited by 0
  7. 2026Constraint-Aware Hierarchical Search for Regulation-Driven Fine-Grained Classificationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Architecture Matters: Comparing RAG Systems under Knowledge Base Poisoning
  2. 2025Agent-UniRAG: A Trainable Open-Source LLM Agent Framework for Unified Retrieval-Augmented Generation Systems
  3. 2026MiRAGE: A Multiagent Framework for Generating Multimodal Multihop Question-Answer Dataset for RAG Evaluation
  4. 2024MAIN-RAG: Multi-Agent Filtering Retrieval-Augmented Generation
  5. 2025RAGCap-Bench: Benchmarking Capabilities of LLMs in Agentic Retrieval Augmented Generation Systems
  6. 2024A Collaborative Multi-Agent Approach to Retrieval-Augmented Generation Across Diverse Data
  7. 2025HM-RAG: Hierarchical Multi-Agent Multimodal Retrieval Augmented Generation
  8. 2025Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG