mlsanityData to 7 Oct 2026

MM-StanceDet: Retrieval-Augmented Multi-modal Multi-agent Stance Detection

arXiv 2604.27934 ↗First posted 30 Apr 2026cs.AI cs.CLcited by 3

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

Abstract (arXiv)

Multimodal Stance Detection (MSD) is crucial for understanding public discourse, yet effectively fusing text and image, especially with conflicting signals, remains challenging. Existing methods often face difficulties with contextual grounding, cross-modal interpretation ambiguity, and single-pass reasoning fragility. To address these, we propose Retrieval-Augmented Multi-modal Multi-agent Stance Detection (MM-StanceDet), a novel multi-agent framework integrating Retrieval Augmentation for contextual grounding, specialized Multimodal Analysis agents for nuanced interpretation, a Reasoning-Enhanced Debate stage for exploring perspectives, and Self-Reflection for robust adjudication. Extensive experiments on five datasets demonstrate MM-StanceDet significantly outperforms state-of-the-art baselines, validating the efficacy of its multi-agent architecture and structured reasoning stages in addressing complex multimodal stance challenges.

Key facts. Cited by 3 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 31 of its 58 references that are in the map. First posted on arXiv 30 Apr 2026.

Builds on

31 of 58 references.

References · 31

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  5. 2023GPT-4 Technical Reportcited by 18,132
  6. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  7. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  8. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  9. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  10. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,317
  11. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,739
  12. 2021ViLT: Vision-and-Language Transformer Without Convolution or Region Supervisioncited by 1,224
19 more
  1. 2023Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debatecited by 995
  2. 2023Vision-Language Models for Vision Tasks: A Surveycited by 834
  3. 2016Stance Detection with Bidirectional Conditional Encodingcited by 93
  4. 2022BridgeTower: Building Bridges Between Encoders in Vision-Language Representation Learningcited by 56
  5. 2023Stance Detection with Collaborative Role-Infused LLM-Based Agentscited by 53
  6. 2024Think Twice Before Trusting: Self-Detection for Large Language Models through Comprehensive Answer Reflectioncited by 40
  7. 2025M2IV: Towards Efficient and Fine-grained Multimodal In-Context Learning via Representation Engineeringcited by 34
  8. 2024Multi-modal Stance Detection: New Datasets and Modelcited by 18
  9. 2024FINEMATCH: Aspect-based Fine-grained Image and Text Mismatch Detection and Correctioncited by 16
  10. 2025Beyond ReAct: A Planner-Centric Framework for Complex Tool-Augmented LLM Reasoningcited by 16
  11. 2025Retrieval-Augmented Dynamic Prompt Tuning for Incomplete Multimodal Learningcited by 15
  12. 2024Multimodal Multi-turn Conversation Stance Detection: A Challenge Dataset and Effective Modelcited by 12
  13. 2025Igniting Creative Writing in Small Language Models: LLM-as-a-Judge versus Multi-Agent Refined Rewardscited by 11
  14. 2025MMM-Fact: A Multimodal, Multi-Domain Fact-Checking Dataset with Multi-Level Retrieval Difficultycited by 5
  15. 2024Acquired TASTE: Multimodal Stance Detection with Textual and Structural Embeddingscited by 3
  16. 2024Breaking Event Rumor Detection via Stance-Separated Multi-Agent Debatecited by 3
  17. 2025Exploring Vision Language Models for Multimodal and Multilingual Stance Detectioncited by 3
  18. 2025EXCLAIM: An Explainable Cross-Modal Agentic System for Misinformation Detection with Hierarchical Retrievalcited by 3
  19. 2026From Manipulation to Mistrust: Explaining Diverse Micro-Video Misinformation for Robust Debunking in the Wildcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Hierarchical Latent Reasoning for LLM-based Recommendationcited by 0
  2. 2026MMDS-Bench: Benchmarking Multimodal Large Language Models on Dynamic Stance in Social Media Interactionscited by 0
  3. 2026AtomRec: Evolving Atomic Memory for Agentic Recommendationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026A Systematic Comparison of Prompting and Multi-Agent Methods for LLM-based Stance Detection
  2. 2025MIND Your Reasoning: A Meta-Cognitive Intuitive-Reflective Network for Dual-Reasoning in Multimodal Stance Detection
  3. 2025Towards Transparent Stance Detection: A Zero-Shot Approach Using Implicit and Explicit Interpretability
  4. 2026Multi-Agent Reasoning with Adaptive Worker Allocation for Stance Detection
  5. 2026StanceFlip: A Comprehensive Multi-Dimensional Benchmark for Multimodal Conversational Stance Flipping Forecasting
  6. 2025Rethinking stance detection: A theoretically-informed research agenda for user-level inference using language models
  7. 2025MT2-CSD: A New Dataset and Multi-Semantic Knowledge Fusion Method for Conversational Stance Detection
  8. 2026StanceMoE: Mixture-of-Experts Architecture for Stance Detection