# MV-Debate: Multi-view Agent Debate with Dynamic Reflection Gating for Multimodal Harmful Content Detection in Social Media

arXiv: https://arxiv.org/abs/2508.05557 · HTML: https://mlsanity.com/paper/2508.05557/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Safety alignment, refusal and guardrails, one of 12 directions in LLM safety and security.
- Builds on 24 of its 43 references that are in the map.
- First posted on arXiv 7 Aug 2025.

## Placed in

- LLM safety and security / [Safety alignment, refusal and guardrails](https://mlsanity.com/safety/safety-alignment-refusal-and-guardrails/)

## Builds on (most cited first, 24 of 24)

- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [Gemma 3 Technical Report](https://mlsanity.com/paper/2503.19786/) (2025)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate](https://mlsanity.com/paper/2308.07201/) (2023)
- [The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes](https://mlsanity.com/paper/2005.04790/) (2020)
- [ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMs](https://mlsanity.com/paper/2309.13007/) (2023)
- [Unleashing the Emergent Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-Collaboration](https://mlsanity.com/paper/2307.05300/) (2023)
- [VideoAgent: A Memory-augmented Multimodal Agent for Video Understanding](https://mlsanity.com/paper/2403.11481/) (2024)
- [Chain of Agents: Large Language Models Collaborating on Long-Context Tasks](https://mlsanity.com/paper/2406.02818/) (2024)
- [The Revolution of Multimodal Large Language Models: A Survey](https://mlsanity.com/paper/2402.12451/) (2024)
- [SNIFFER: Multimodal Large Language Model for Explainable Out-of-Context Misinformation Detection](https://mlsanity.com/paper/2403.03170/) (2024)
- [PRISM: Self-Pruning Intrinsic Selection Method for Training-Free Multimodal Data Selection](https://mlsanity.com/paper/2502.12119/) (2025)
- [Let Models Speak Ciphers: Multiagent Debate through Embeddings](https://mlsanity.com/paper/2310.06272/) (2023)
- [LLaVA Steering: Visual Instruction Tuning with 500x Fewer Parameters through Modality Linear Representation-Steering](https://mlsanity.com/paper/2412.12359/) (2024)
- [CoT-Kinetics: A Theoretical Modeling Assessing LRM Reasoning Process](https://mlsanity.com/paper/2505.13408/) (2025)
- [CLOVA: A Closed-Loop Visual Assistant with Tool Usage and Update](https://mlsanity.com/paper/2312.10908/) (2023)
- [MLLM-CompBench: A Comparative Reasoning Benchmark for Multimodal LLMs](https://mlsanity.com/paper/2407.16837/) (2024)
- [RepoMaster: Autonomous Exploration and Understanding of GitHub Repositories for Complex Task Solving](https://mlsanity.com/paper/2505.21577/) (2025)
- [DebUnc: Improving Large Language Model Agent Communication With Uncertainty Metrics](https://mlsanity.com/paper/2407.06426/) (2024)
- [Detecting and Correcting Hate Speech in Multimodal Memes with Large Visual Language Model](https://mlsanity.com/paper/2311.06737/) (2023)
- [Multimodal Fact-Checking with Vision Language Models: A Probing Classifier based Solution with Embedding Strategies](https://mlsanity.com/paper/2412.05155/) (2024)
- [Understanding Museum Exhibits using Vision-Language Reasoning](https://mlsanity.com/paper/2412.01370/) (2024)

## Built on by (most cited first, 4 of 4)

- [TECP: Token-Entropy Conformal Prediction for LLMs](https://mlsanity.com/paper/2509.00461/) (2025)
- [Set-Valued Prediction for Large Language Models with Feasibility-Aware Coverage Guarantees](https://mlsanity.com/paper/2603.22966/) (2026)
- [Child-Oriented AIGC Video Risk Reviewing: A Benchmark and Knowledge-Supported Iterative Reasoning Framework](https://mlsanity.com/paper/2607.22715/) (2026)
- [Towards High-Level Semantic Intelligence](https://mlsanity.com/paper/2607.24082/) (2026)

## Abstract (arXiv)

Social media has evolved into a complex multimodal environment where text, images, and other signals interact to shape nuanced meanings, often concealing harmful intent. Identifying such intent, whether sarcasm, hate speech, or misinformation, remains challenging due to cross-modal contradictions, rapid cultural shifts, and subtle pragmatic cues. To address these challenges, we propose MV-Debate, a multi-view agent debate framework with dynamic reflection gating for unified multimodal harmful content detection. MV-Debate assembles four complementary debate agents, a surface analyst, a deep reasoner, a modality contrast, and a social contextualist, to analyze content from diverse interpretive perspectives. Through iterative debate and reflection, the agents refine responses under a reflection-gain criterion, ensuring both accuracy and efficiency. Experiments on three benchmark datasets demonstrate that MV-Debate significantly outperforms strong single-model and existing multi-agent debate baselines. This work highlights the promise of multi-agent debate in advancing reliable social intent detection in safety-critical online contexts.