Contestable Multi-Agent Debate with Arena-based Argumentative Computation for Multimedia Verification
For multimedia verification tasks requiring transparency and contestability, this work provides a practical framework combining argumentation and LLMs, though it is an incremental submission to a grand challenge without reported quantitative results.
The paper proposes a contestable multi-agent framework for multimedia verification that integrates multimodal LLMs, external tools, and arena-based quantitative bipolar argumentation to produce transparent, editable verification reports. The system decomposes cases into sections, retrieves evidence, and resolves arguments via local graphs with clash resolution and uncertainty-aware escalation.
Multimedia verification requires not only accurate conclusions but also transparent and contestable reasoning. We propose a contestable multi-agent framework that integrates multimodal large language models, external verification tools, and arena-based quantitative bipolar argumentation (A-QBAF) as a submission to the ICMR 2026 Grand Challenge on Multimedia Verification. Our method decomposes each case into claim-centered sections, retrieves targeted evidence, and converts evidence into structured support and attack arguments with provenance and strength scores. These arguments are resolved through small local argument graphs with selective clash resolution and uncertainty-aware escalation. The resulting system generates section-wise verification reports that are transparent, editable, and computationally practical for real-world multimedia verification. Our implementation is public at: https://github.com/Analytics-Everywhere-Lab/MV2026_the_liems.