VILLAIN at AVerImaTeC: Verifying Image-Text Claims via Multi-Agent Collaboration

Research Summary

Contribution Summary

• This paper describes VILLAIN, a multimodal fact-checking system that verifies image-text claims through prompt-based multi-agent collaboration.
• For the AVerImaTeC shared task, VILLAIN employs vision-language model agents across multiple stages of fact-checking.
• Textual and visual evidence is retrieved from the knowledge store enriched through additional web collection.

Why It Matters For Eval

• This paper describes VILLAIN, a multimodal fact-checking system that verifies image-text claims through prompt-based multi-agent collaboration.
• For the AVerImaTeC shared task, VILLAIN employs vision-language model agents across multiple stages of fact-checking.

Related Papers

• STaRR: Spatial-Temporal Token-Dynamics-Aware Responsive Remasking for Diffusion Language Models Embedding Neighbor
• Evaluating the Usage of African-American Vernacular English in Large Language Models Embedding Neighbor
• Share Your Attention: Transformer Weight Sharing via Matrix-based Dictionary Learning Embedding Neighbor
• Colosseum: Auditing Collusion in Cooperative Multi-Agent Systems Embedding Neighbor
• SELAUR: Self Evolving LLM Agent via Uncertainty-aware Rewards Embedding Neighbor
• Towards single-shot coherent imaging via overlap-free ptychography Embedding Neighbor
• NanoKnow: How to Know What Your Language Model Knows Embedding Neighbor
• Evolving Language Models without Labels: Majority Drives Selection, Novelty Promotes Variation Embedding Neighbor
• Residual Connections and the Causal Shift: Uncovering a Structural Misalignment in Transformers Embedding Neighbor
• Inner Speech as Behavior Guides: Steerable Imitation of Diverse Behaviors for Human-AI coordination Tag Overlap
• CORE: Measuring Multi-Agent LLM Interaction Quality under Game-Theoretic Pressures Tag Overlap
• Team of Thoughts: Efficient Test-time Scaling of Agentic Systems through Orchestrated Tool Calling Tag Overlap