用大模型协同多个检测器，自动分析图像真伪并给出解释。
AgentFoX: LLM Agent-Guided Fusion with eXplainability for AI-Generated Image Detection
- 大模型调度多个专家检测器，收集语义与信号级证据。
- 在复杂生成和处理条件下，检测准确率显著优于现有方法。
- 适合需要可解释性检测结果的AI安全、内容审核场景。
AI生成图像（AIGI）的真实性给可靠取证检测带来了日益严峻的挑战，不同来源的生成模型和后处理条件导致异构专家检测器产生冲突预测。现有多专家融合方法依赖固定规则或学习策略，难以评估样本特定可靠性、严谨解决冲突，也缺乏基于证据的解释能力。我们提出AgentFoX，一种由大模型驱动的代理式多专家框架，通过指令-推理核心实现证据融合。依据预设规范，核心协调子任务以收集语义与信号级证据，基于结构化上下文推理真伪，并生成可审计的报告以支持可解释性。在此过程中，构建模型中心的专家画像用于可靠性评估，数据中心的聚类画像用于上下文分析，共同建立冲突化解的证据背景。在多个基准上的广泛评估表明，AgentFoX在复杂条件下具备优异的鲁棒性与泛化能力。
原文摘要 · Abstract (English)
The realism of AI-generated images (AIGI) poses increasing challenges for reliable forensic detection, where heterogeneous expert detectors may produce conflicting predictions across diverse generative sources and post-processing conditions. Existing multi-expert fusion methods rely on fixed rules or learned fusion strategies, offering limited ability to assess sample-specific reliability, execute rigorous adjudication of conflicts, and provide evidence-grounded explanations. We propose AgentFoX, an LLM-driven agentic multi-expert framework for AIGI detection that employs a command-and-reasoning core to perform evidence fusion. Following predefined guidelines, the core coordinates designated subtasks to collect semantic and signal-level evidence, reason over structured contexts to determine authenticity, and generate an auditable report for explainability. During this process, Expert Profiles are constructed for model-centric reliability assessment, while Clustering Profiles are built for data-centric contextual analysis, jointly establishing evidence contexts for conflict resolution. Extensive evaluations across diverse benchmarks demonstrate the robustness and generalizability of AgentFoX under complex conditions.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。