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

arXiv: https://arxiv.org/abs/2602.04587 · HTML: https://mlsanity.com/paper/2602.04587/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use.
- Builds on 8 of its 14 references that are in the map.
- First posted on arXiv 4 Feb 2026.

## Placed in

- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 8 of 8)

- [Small Language Models are the Future of Agentic AI](https://mlsanity.com/paper/2506.02153/) (2025)
- [AVeriTeC: A Dataset for Real-world Claim Verification with Evidence from the Web](https://mlsanity.com/paper/2305.13117/) (2023)
- [The Automated Verification of Textual Claims (AVeriTeC) Shared Task](https://mlsanity.com/paper/2410.23850/) (2024)
- [Ev2R: Evaluating Evidence Retrieval in Automated Fact-Checking](https://mlsanity.com/paper/2411.05375/) (2024)
- [AVerImaTeC: A Dataset for Automatic Verification of Image-Text Claims with Evidence from the Web](https://mlsanity.com/paper/2505.17978/) (2025)
- [HerO at AVeriTeC: The Herd of Open Large Language Models for Verifying Real-World Claims](https://mlsanity.com/paper/2410.12377/) (2024)
- [Team HUMANE at AVeriTeC 2025: HerO 2 for Efficient Fact Verification](https://mlsanity.com/paper/2507.11004/) (2025)
- [AIC CTU@FEVER 8: On-premise fact checking through long context RAG](https://mlsanity.com/paper/2508.04390/) (2025)

## Abstract (arXiv)

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. To identify key information and address inconsistencies among evidence items, modality-specific and cross-modal agents generate analysis reports. In the subsequent stage, question-answer pairs are produced based on these reports. Finally, the Verdict Prediction agent produces the verification outcome based on the image-text claim and the generated question-answer pairs. Our system ranked first on the leaderboard across all evaluation metrics. The source code is publicly available at https://github.com/ssu-humane/VILLAIN.